INDEX

Explanations

expressions of personal preferences and desires

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ø§Ø·

-0.15

 Ïį

-0.14

duck

-0.14

æ¯

-0.14

ÑĢÑĥÑģ

-0.14

alace

-0.14

 xÃºc

-0.13

Paz

-0.13

ÙĪÙĦØ§

-0.13

reib

-0.13

POSITIVE LOGITS

 hoped

0.46

 ideal

0.44

 hope

0.41

å¸ĮæľĽ

0.40

 hopes

0.39

 hoping

0.38

Hope

0.36

 Ideal

0.36

 Hope

0.35

hope

0.35

Activations Density 0.095%

expressions of personal preferences and desires

No Comments

No Known Activations