INDEX

Explanations

instances of the word "object" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Fro

-0.16

ucket

-0.14

elon

-0.14

iere

-0.14

COPE

-0.14

_compat

-0.14

ëŀĮ

-0.14

 Widow

-0.13

ÂłPS

-0.13

å·

-0.13

POSITIVE LOGITS

 Dear

0.17

 sterling

0.16

atsby

0.16

arcy

0.15

ë£Į

0.15

encial

0.14

osed

0.14

æĽ°

0.14

RoleId

0.14

ularity

0.14

Activations Density 0.021%

instances of the word "object" and related terms

No Comments

No Known Activations