INDEX

Explanations

references to judicial decisions and legal processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.16

 electrom

-0.15

ÑıÐ½

-0.14

tal

-0.14

 candle

-0.14

 BÄ°L

-0.14

izzo

-0.14

 DISCLAIM

-0.14

ç½²

-0.14

 Candle

-0.13

POSITIVE LOGITS

rena

0.16

azers

0.15

dzi

0.15

 deal

0.15

exas

0.15

ilated

0.15

 mainScreen

0.14

 show

0.14

'h

0.14

ilar

0.14

Activations Density 0.028%

references to judicial decisions and legal processes

No Comments

No Known Activations