INDEX

Explanations

content related to free speech and its legal implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

-0.15

iju

-0.14

gett

-0.14

 Wallpaper

-0.14

Ð¾ÐºÐ¾Ð»

-0.14

loggedin

-0.14

fm

-0.14

acin

-0.13

 electr

-0.13

POSITIVE LOGITS

 speech

0.51

 Speech

0.46

 First

0.44

speech

0.42

Speech

0.42

 free

0.39

peech

0.36

 freedom

0.34

First

0.32

free

0.31

Activations Density 0.197%

content related to free speech and its legal implications

No Comments

No Known Activations