INDEX

Explanations

references to swimming tests and metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ucer

-0.16

wagon

-0.16

éĮ²

-0.15

 liquidity

-0.14

 UIResponder

-0.14

ibri

-0.14

æ¶²

-0.14

ÑģÑĤÑĥÐ¿

-0.14

ìķ¡

-0.14

 Sweat

-0.13

POSITIVE LOGITS

 stroke

0.34

 Stroke

0.31

 strokes

0.31

Stroke

0.30

stroke

0.29

 breast

0.25

 Breast

0.25

 kick

0.24

fre

0.24

 butterfly

0.24

Activations Density 0.018%

references to swimming tests and metrics

No Comments

No Known Activations