INDEX

Explanations

references to specific points in time or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

asename

-0.15

ë¦¼

-0.14

Dia

-0.14

ichert

-0.14

zer

-0.14

bru

-0.13

owell

-0.13

æĦĽ

-0.13

Scripts

-0.13

POSITIVE LOGITS

-le

0.17

 baise

0.16

 workplace

0.16

rosse

0.16

phia

0.16

 occasions

0.15

egin

0.15

 disposal

0.15

orney

0.15

unes

0.15

Activations Density 0.092%

references to specific points in time or conditions

No Comments

No Known Activations