INDEX

Explanations

references to specific gene companies or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

endas

-0.19

inger

-0.17

igrams

-0.16

otland

-0.16

DV

-0.15

AFE

-0.15

inge

-0.15

portun

-0.15

 Followers

-0.14

inges

-0.14

POSITIVE LOGITS

apping

0.17

TRL

0.17

trl

0.16

swire

0.16

ghi

0.16

Ã¡zev

0.16

rega

0.15

ras

0.15

ki

0.15

rf

0.15

Activations Density 0.022%

references to specific gene companies or organizations

No Comments

No Known Activations