INDEX

Explanations

mentions of measurements, dimensions, or specifications related to physical objects

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

\CMS

-0.15

à¸ķà¸£

-0.14

asti

-0.13

 Bang

-0.13

ogan

-0.13

cÃŃ

-0.13

-scalable

-0.12

PELL

-0.12

ate

-0.12

Ļæ±Ł

-0.12

POSITIVE LOGITS

wert

0.15

riot

0.15

erator

0.15

tryside

0.15

igner

0.15

áº©u

0.14

lovak

0.14

ibaba

0.14

AtA

0.14

agini

0.14

Activations Density 0.207%

mentions of measurements, dimensions, or specifications related to physical objects

No Comments

No Known Activations