INDEX

Explanations

programming-related keywords and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ivas

-0.16

SYS

-0.15

WB

-0.14

pii

-0.14

GB

-0.14

Î¼Î¯

-0.14

utschein

-0.13

ighb

-0.13

ysz

-0.13

POSITIVE LOGITS

æ·¡

0.16

enne

0.15

enan

0.15

odied

0.15

_kwargs

0.15

ç½²

0.14

jected

0.14

ogue

0.14

ktor

0.14

ovna

0.14

Activations Density 0.283%

programming-related keywords and terminology

No Comments

No Known Activations