INDEX

Explanations

references to insertion commands and syntax in code or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

lesia

-0.17

eldon

-0.16

alar

-0.15

Î»Î¿Î½

-0.15

Ø¨Ø§ÙĨ

-0.14

çķª

-0.14

beros

-0.14

rous

-0.14

itet

-0.14

allee

-0.14

POSITIVE LOGITS

inh

0.16

 Pace

0.15

agi

0.15

isko

0.14

è¢ĸ

0.14

 forth

0.14

Ð¼ÐµÐ½ÑĪ

0.14

urname

0.13

æĢ

0.13

mag

0.13

Activations Density 0.096%

references to insertion commands and syntax in code or programming contexts

No Comments

No Known Activations