INDEX

Explanations

phrases related to gaining knowledge or information

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

acher

-0.17

.mount

-0.16

Sez

-0.15

Lau

-0.15

Vak

-0.15

ëĵ

-0.14

illions

-0.14

ercul

-0.14

ennon

-0.13

POSITIVE LOGITS

annt

0.15

elas

0.15

uid

0.15

leaf

0.14

 Bram

0.14

idata

0.14

yk

0.14

/animate

0.14

 crow

0.13

Î¸Î·

0.13

Activations Density 0.013%

phrases related to gaining knowledge or information

No Comments

No Known Activations