INDEX

Explanations

phrases that indicate negation or non-existence

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

/MIT

-0.17

oeff

-0.16

qq

-0.15

amoto

-0.15

æł

-0.15

Nam

-0.14

aspers

-0.14

ä¹İ

-0.14

allen

-0.14

jee

-0.14

POSITIVE LOGITS

ÑĩÐ¸Ð½

0.16

Ã©tÃ©

0.15

akens

0.15

ovice

0.15

å»·

0.14

ucch

0.14

aket

0.14

enerate

0.14

resher

0.14

 chin

0.14

Activations Density 0.237%

phrases that indicate negation or non-existence

No Comments

No Known Activations