INDEX

Explanations

source code and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

rana

-0.16

lam

-0.15

oney

-0.15

Äħd

-0.14

æ

-0.14

jah

-0.14

lica

-0.13

 íķĺëĤĺ

-0.13

convert

-0.13

conv

-0.13

POSITIVE LOGITS

 Ð²Ð¾ÑģÐ¿

0.15

ichel

0.15

ibri

0.15

aises

0.14

ÄįÃŃ

0.14

pressor

0.14

ãģ¨ãģĨ

0.14

 Ø³Ø±Ùħ

0.14

 Genuine

0.14

è¿·

0.14

Activations Density 0.121%

source code and programming constructs

No Comments

No Known Activations