INDEX

Explanations

affirmative statements or expressions of agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ANEL

-0.16

Hoe

-0.15

æ¡Ĳ

-0.15

wick

-0.15

IRC

-0.14

Fil

-0.14

caret

-0.14

Ã¶rt

-0.14

alyzed

-0.14

ALAR

-0.14

POSITIVE LOGITS

addock

0.17

æŀľ

0.16

PropTypes

0.14

cq

0.14

 Ð¾Ð±ÑĢÐ°ÑĤ

0.14

 cháº¯n

0.14

ingly

0.14

bia

0.14

 Hundred

0.14

Activations Density 0.014%

affirmative statements or expressions of agreement

No Comments

No Known Activations