INDEX

Explanations

expressions of mixed opinions or complex character evaluations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onis

-0.17

nad

-0.15

iet

-0.15

agar

-0.15

arya

-0.15

ute

-0.15

orsi

-0.15

eliac

-0.15

 eldre

-0.14

ulant

-0.14

POSITIVE LOGITS

 combination

0.41

 neither

0.41

 combinations

0.40

 none

0.39

 somewhere

0.36

 Combination

0.35

combination

0.35

 Neither

0.33

 both

0.32

 everything

0.32

Activations Density 0.114%

expressions of mixed opinions or complex character evaluations

No Comments

No Known Activations