INDEX

Explanations

instances of the word "work" along with related terms indicating artistic or creative expressions and influences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ENDOR

-0.16

phin

-0.15

ulle

-0.15

Ú¯Ø§Ø±

-0.14

endale

-0.14

asu

-0.14

loquent

-0.14

engkap

-0.14

Ãª

-0.14

 Hlav

-0.14

POSITIVE LOGITS

wright

0.16

0.15

clusive

0.15

utherford

0.14

 tangent

0.14

 Blur

0.13

 revers

0.13

ives

0.13

weep

0.13

ìĸĳ

0.13

Activations Density 0.155%

instances of the word "work" along with related terms indicating artistic or creative expressions and influences

No Comments

No Known Activations