INDEX

Explanations

references to wheelchairs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

dÃ¼l

-0.16

dense

-0.16

ittel

-0.15

yne

-0.15

tle

-0.15

oulos

-0.15

enthal

-0.15

ional

-0.15

olta

-0.14

lope

-0.14

POSITIVE LOGITS

chair

0.43

wright

0.32

bar

0.31

ie

0.30

-chair

0.28

 chair

0.28

base

0.28

Chair

0.28

house

0.28

ing

0.27

Activations Density 0.012%

references to wheelchairs

No Comments

No Known Activations