INDEX

Explanations

expressions of uncertainty and inquiries about information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Flesh

-0.15

zin

-0.14

 Witnesses

-0.14

 diagn

-0.14

emo

-0.13

à¸´à¸ķà¸£

-0.13

POSITIVE LOGITS

 find

0.30

 couldn

0.30

 found

0.29

 finds

0.29

æī¾åĪ°

0.28

 Found

0.28

æī¾

0.28

found

0.27

find

0.27

couldn

0.27

Activations Density 0.099%

expressions of uncertainty and inquiries about information

No Comments

No Known Activations