INDEX

Explanations

specific locations and geographic identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

çıł

-0.19

ãĤ¨

-0.17

å®ĭä½ĵ

-0.17

Î¸ÎŃ

-0.16

croll

-0.16

á»ĵi

-0.15

åŁĥ

-0.15

uese

-0.15

thew

-0.15

esda

-0.15

POSITIVE LOGITS

jack

0.18

ãĤ¯ãĥª

0.16

 jack

0.16

-M

0.16

Jack

0.15

 Jack

0.15

agger

0.15

-T

0.15

ak

0.15

×ŀ

0.15

Activations Density 0.049%

specific locations and geographic identifiers

No Comments

No Known Activations