INDEX

Explanations

discussions about extremes and balance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

imas

-0.17

ceil

-0.16

olas

-0.16

vault

-0.15

oola

-0.15

 Giang

-0.15

ÏģÎ¿Ïħ

-0.14

inh

-0.14

elight

-0.14

engin

-0.13

POSITIVE LOGITS

 intermediate

0.54

 middle

0.47

 Intermediate

0.45

Intermediate

0.42

middle

0.40

 intermediary

0.40

 intermedi

0.37

 somewhere

0.37

 midd

0.37

 between

0.36

Activations Density 0.206%

discussions about extremes and balance

No Comments

No Known Activations