INDEX

Explanations

words expressing feelings of disdain, scorn, or contempt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Bram

-0.15

ì»¤

-0.15

Ø¶ÛĮ

-0.14

 Kern

-0.14

_IGNORE

-0.14

 Penn

-0.14

queeze

-0.14

endance

-0.13

åŃĲãģ¯

-0.13

POSITIVE LOGITS

ible

0.16

sure

0.16

anka

0.16

ky

0.15

agini

0.15

agas

0.15

kle

0.15

akash

0.14

Ã¼nchen

0.14

mann

0.14

Activations Density 0.011%

words expressing feelings of disdain, scorn, or contempt

No Comments

No Known Activations