INDEX

Explanations

specific locations, particularly names of cities

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

[js

-0.16

 kÃ¥

-0.15

uze

-0.15

Î»Î®

-0.15

/exp

-0.14

hee

-0.13

cez

-0.13

ationally

-0.13

.toolbox

-0.13

Î»Î¿Ïħ

-0.13

POSITIVE LOGITS

/Framework

0.17

ilder

0.15

coma

0.14

kÄ±r

0.14

abilit

0.14

ixon

0.14

Ð¸Ð¼ÐµÑĢ

0.14

wick

0.14

 corner

0.14

åºŃ

0.14

Activations Density 0.000%

specific locations, particularly names of cities

No Comments

No Known Activations