INDEX

Explanations

references to books and book-related terms

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

most

-0.17

igm

-0.16

est

-0.16

abelle

-0.15

ilt

-0.15

hir

-0.15

wner

-0.14

agon

-0.14

POSITIVE LOGITS

ç±į

0.20

worm

0.19

stores

0.17

shelf

0.17

ÑģÑıÑĤ

0.16

TexParameteri

0.15

eller

0.15

ellers

0.15

iyat

0.15

illion

0.14

Activations Density 0.069%

references to books and book-related terms

No Comments

No Known Activations