INDEX

Explanations

numerical references or identifiers related to scientific publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

inks

-0.17

eva

-0.15

amax

-0.15

 Mick

-0.15

 Conc

-0.14

ãĤ§

-0.14

eld

-0.14

irk

-0.14

ivant

-0.14

omatic

-0.14

POSITIVE LOGITS

ulg

0.16

omm

0.15

omaly

0.15

Î¬Î½Î±

0.15

addtogroup

0.14

 Ä°z

0.14

AUSE

0.14

inha

0.14

LETTE

0.14

ìŀĲìĿ¸

0.14

Activations Density 0.000%

numerical references or identifiers related to scientific publications

No Comments

No Known Activations