INDEX

Explanations

specific historical references and numerical data related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ANGO

-0.14

adden

-0.14

 refusal

-0.13

JK

-0.13

 Mort

-0.13

embros

-0.13

atty

-0.13

antino

-0.13

&e

-0.13

att

-0.13

POSITIVE LOGITS

erne

0.25

end

0.19

 komple

0.19

neu

0.19

 wieder

0.19

 restaur

0.18

suk

0.18

umb

0.18

 rest

0.18

 voll

0.17

Activations Density 0.016%

specific historical references and numerical data related to events

No Comments

No Known Activations