INDEX

Explanations

comments and documentation in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aida

-0.15

ÃĸL

-0.15

onica

-0.15

loub

-0.14

ause

-0.14

CLUDING

-0.14

iola

-0.13

olec

-0.13

isas

-0.13

yk

-0.13

POSITIVE LOGITS

-UA

0.16

enger

0.15

erring

0.15

IALIZED

0.15

aways

0.14

ÛĮØ§ÙĨ

0.14

-Requested

0.13

/plain

0.13

PHA

0.13

 Administrative

0.13

Activations Density 0.081%

comments and documentation in code

No Comments

No Known Activations