INDEX

Explanations

expressions of personal experiences or highlights in conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

adesh

-0.16

pagen

-0.14

ulis

-0.14

zos

-0.14

abd

-0.14

Ð½Ð¸ÑĨÐµ

-0.14

vant

-0.14

pac

-0.14

 liá»ģn

-0.14

Ãłng

-0.13

POSITIVE LOGITS

 ever

0.56

 EVER

0.43

ever

0.37

-ever

0.37

 Ever

0.37

Ever

0.35

 jamais

0.30

EVER

0.27

 anybody

0.23

 possibly

0.23

Activations Density 0.033%

expressions of personal experiences or highlights in conversations

No Comments

No Known Activations