INDEX

Explanations

instances of the word 'Unlike' to emphasize contrasts or comparisons

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ichen

-0.17

antar

-0.16

chen

-0.15

Ä±sÄ±t

-0.15

UFFIX

-0.15

Î¼Î¼

-0.14

icture

-0.14

isko

-0.14

isman

-0.14

Ð»Ð¾Ð´

-0.14

POSITIVE LOGITS

olly

0.15

edd

0.15

ĸī

0.14

à¸²à¸£à¸ĸ

0.14

arend

0.14

Î³Î·

0.14

 nhau

0.14

SPAN

0.13

é¤

0.13

orp

0.13

Activations Density 0.006%

instances of the word 'Unlike' to emphasize contrasts or comparisons

No Known Activations