INDEX

Explanations

punctuation marks and quotes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

alem

-0.16

.infinity

-0.14

.assertIs

-0.14

Å¼y

-0.14

ield

-0.14

ismet

-0.14

ÅŁt

-0.13

zk

-0.13

ashi

-0.13

xfd

-0.13

POSITIVE LOGITS

Ãºt

0.18

0.16

0.15

egin

0.15

 fitte

0.15

rest

0.14

 çģ

0.14

Activations Density 0.002%

punctuation marks and quotes

No Comments

No Known Activations