INDEX

Explanations

phrases related to reputation and public perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ellow

-0.20

nemonic

-0.16

erman

-0.15

aths

-0.14

oblin

-0.14

íĮ

-0.14

Ð¼Ðµ

-0.13

/root

-0.13

æĥ

-0.13

 Ø¹Ø²

-0.13

POSITIVE LOGITS

alternative

0.15

Alternative

0.14

ixe

0.14

STALL

0.14

 Ø³Ø®

0.14

nick

0.14

land

0.14

 Bout

0.14

SGlobal

0.13

Detach

0.13

Activations Density 0.014%

phrases related to reputation and public perception

No Comments

No Known Activations