INDEX

Explanations

mentions of prohibited items or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

utor

-0.20

plus

-0.15

alla

-0.15

field

-0.14

 Plus

-0.14

 plus

-0.14

go

-0.14

obar

-0.14

avl

-0.14

POSITIVE LOGITS

/epl

0.16

ç·Ĵ

0.16

endcode

0.16

@nate

0.16

_mD

0.16

:Object

0.15

Äıte

0.15

SPATH

0.15

\common

0.15

_mE

0.15

Activations Density 0.030%

mentions of prohibited items or behaviors

No Comments

No Known Activations