INDEX

Explanations

references to time, specifically years and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ildo

-0.16

isu

-0.16

isposable

-0.15

meni

-0.14

 èĩªåĬ¨çĶŁæĪĲ

-0.14

imals

-0.14

ILD

-0.14

 Micha

-0.14

CTYPE

-0.13

ild

-0.13

POSITIVE LOGITS

0.16

 same

0.16

aux

0.15

nero

0.14

umen

0.14

isz

0.14

-framework

0.14

end

0.14

 following

0.14

Activations Density 0.083%

references to time, specifically years and dates

No Comments

No Known Activations