INDEX

Explanations

references to web browsers and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

adÃŃ

-0.18

yon

-0.16

åĦ¿

-0.15

ories

-0.15

obbies

-0.14

irs

-0.14

yth

-0.14

yor

-0.14

serter

-0.14

POSITIVE LOGITS

bilt

0.15

hots

0.15

ç¿°

0.15

CAF

0.15

ë§ģ

0.15

mob

0.14

Ð¸Ð½Ð³

0.14

/client

0.14

-only

0.14

olatile

0.13

Activations Density 0.022%

references to web browsers and related terms

No Comments

No Known Activations