INDEX

Explanations

references to purchasing or shopping items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

igne

-0.15

 Curtain

-0.15

 thumbs

-0.15

ogle

-0.14

ppe

-0.14

 Commonwealth

-0.14

 Brill

-0.14

aman

-0.14

 crack

-0.14

anel

-0.13

POSITIVE LOGITS

omed

0.16

reau

0.16

imb

0.15

oron

0.15

º«

0.15

 purch

0.15

 éĢļ

0.15

erton

0.15

éł

0.15

 novelty

0.15

Activations Density 0.309%

references to purchasing or shopping items

No Comments

No Known Activations