INDEX

Explanations

files and documentation related to programming or development

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

_alg

-0.14

ims

-0.14

 Ernest

-0.14

iqu

-0.14

 Strat

-0.14

 Estr

-0.14

ÙĬÙĪÙĨ

-0.14

_ser

-0.14

-0.13

ãģıãĤĮãģŁ

-0.13

POSITIVE LOGITS

à¸«à¸¡à¸²à¸¢

0.16

ripp

0.16

 seiz

0.16

 depress

0.16

.fd

0.15

apol

0.15

preci

0.15

swire

0.15

Ã¼ss

0.14

neau

0.14

Activations Density 0.470%

files and documentation related to programming or development

No Comments

No Known Activations