INDEX

Explanations

programming syntax and commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

idos

-0.15

ÙĥØ§Øª

-0.15

 roma

-0.15

laus

-0.15

Ã¼rn

-0.14

iquer

-0.14

ÑĥÐ²

-0.14

YLON

-0.14

 Wonderland

-0.13

uploaded

-0.13

POSITIVE LOGITS

 POSIX

0.19

 posix

0.18

 tell

0.18

ke

0.16

 Â¬

0.16

 Specialists

0.15

_FRONT

0.15

ign

0.15

posix

0.15

oyal

0.14

Activations Density 0.005%

programming syntax and commands

No Comments

No Known Activations