INDEX

Explanations

intensifiers that emphasize opinions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 ever

-0.17

Ã¡vÄĽ

-0.15

ÑĭÑħ

-0.15

sic

-0.15

 somewhat

-0.14

ÑĭÑģ

-0.14

opyright

-0.14

ict

-0.14

vig

-0.14

ÏĢÎ·

-0.14

POSITIVE LOGITS

yyyy

0.20

much

0.17

 much

0.17

yyy

0.16

/ext

0.16

yy

0.16

ë¨¸ëĭĪ

0.15

eur

0.15

DOC

0.14

 pháº©m

0.14

Activations Density 0.061%

intensifiers that emphasize opinions or sentiments

No Comments

No Known Activations