INDEX

Explanations

words and phrases indicating involvement or engagement in various contexts

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

sek

-0.16

ean

-0.15

auc

-0.15

ìĽĮíģ¬

-0.15

 ChÃ¢u

-0.15

pecies

-0.14

åŀ

-0.14

-java

-0.14

 tiÃªu

-0.14

ÐºÐ¾Ð»

-0.14

POSITIVE LOGITS

0.17

McN

0.15

igma

0.15

 Rosen

0.15

 comm

0.15

igan

0.14

izr

0.14

imi

0.14

 neighborhood

0.14

Activations Density 0.023%

words and phrases indicating involvement or engagement in various contexts

No Comments

No Known Activations