INDEX

Explanations

links to websites and online resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ROUGH

-0.17

Ãºa

-0.15

unning

-0.15

arn

-0.14

ega

-0.14

well

-0.14

imp

-0.13

ide

-0.13

um

-0.13

 suicides

-0.13

POSITIVE LOGITS

ãĥķãĤ

0.16

ieu

0.14

|--

0.14

.ua

0.14

xious

0.14

FIXME

0.14

 meis

0.13

.TypeOf

0.13

edback

0.13

æł·çļĦ

0.13

Activations Density 0.009%

links to websites and online resources

No Comments

No Known Activations