INDEX

Explanations

references to historical events and their representation in media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Themes

-0.15

 temas

-0.14

éĩįçĤ¹

-0.13

ombat

-0.13

abra

-0.13

usalem

-0.13

Mods

-0.13

çĭ¬

-0.12

Topics

-0.12

acom

-0.12

POSITIVE LOGITS

 newspapers

0.43

 books

0.39

 newspaper

0.38

 textbooks

0.37

 magazines

0.36

 literature

0.35

 publications

0.34

 journals

0.33

 documentaries

0.31

 published

0.30

Activations Density 0.402%

references to historical events and their representation in media

No Comments

No Known Activations