INDEX

Explanations

hyperlinks or references to documents and files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Î¸Î¼

-0.16

inou

-0.15

rts

-0.15

perience

-0.15

olumn

-0.14

 Î²Î±

-0.14

LocalizedMessage

-0.14

clamation

-0.14

arton

-0.14

etter

-0.14

POSITIVE LOGITS

anson

0.15

zp

0.14

URED

0.14

Pur

0.14

Ã¼y

0.13

ATER

0.13

ieder

0.13

zelf

0.13

Activations Density 0.004%

hyperlinks or references to documents and files

No Comments

No Known Activations