INDEX

Explanations

references to authors and their written works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

lez

-0.19

ioni

-0.18

lint

-0.15

ona

-0.15

éĲĺ

-0.14

ian

-0.14

lein

-0.14

svc

-0.14

Advisor

-0.14

able

-0.14

POSITIVE LOGITS

aturas

0.15

EDIA

0.15

FG

0.14

 Atlantic

0.14

.opensource

0.14

elter

0.14

Atlantic

0.14

.Scheme

0.14

MBER

0.14

	throws

0.13

Activations Density 0.023%

references to authors and their written works

No Comments

No Known Activations