INDEX

Explanations

programming-related hooks and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ee

-0.16

apa

-0.16

noh

-0.15

GH

-0.15

æĢģ

-0.15

 stride

-0.14

yna

-0.14

usch

-0.14

 Mutual

-0.14

 Green

-0.13

POSITIVE LOGITS

enstein

0.20

aeda

0.17

.removeListener

0.16

ibold

0.16

)prepare

0.16

Ã±ana

0.15

odox

0.15

Ð´Ð¾Ð½

0.15

Ñİ

0.15

addock

0.15

Activations Density 0.047%

programming-related hooks and functions

No Comments

No Known Activations