INDEX

Explanations

instances of the word "judge" and its variations, focusing on the theme of judgment or assessment

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

thon

-0.17

kes

-0.17

bon

-0.17

adolu

-0.16

adem

-0.15

logue

-0.14

inx

-0.14

idae

-0.14

Äĥ

-0.14

oÅ¾

-0.14

POSITIVE LOGITS

multipart

0.15

ÙĪØªÛĮ

0.14

è·Ŀ

0.14

ven

0.14

 favor

0.14

 Leer

0.13

 Balt

0.13

-quarters

0.13

 Weston

0.13

Activations Density 0.028%

instances of the word "judge" and its variations, focusing on the theme of judgment or assessment

No Comments

No Known Activations