INDEX

Explanations

references to specific pipelines and related locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.16

ï¸ı

-0.16

yd

-0.15

ÛĮ

-0.15

ercul

-0.15

erer

-0.15

-0.14

zelf

-0.14

lec

-0.14

ÛĮØ§Øª

-0.14

POSITIVE LOGITS

ously

0.19

ware

0.17

odd

0.17

stick

0.15

ments

0.15

Ľ°

0.15

WARE

0.15

qual

0.14

zed

0.14

stell

0.14

Activations Density 0.256%

references to specific pipelines and related locations

No Comments

No Known Activations