INDEX

Explanations

references to court-related terminology and legal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ith

-0.16

 trace

-0.16

usal

-0.15

cast

-0.15

cej

-0.14

abus

-0.14

(trace

-0.14

refund

-0.14

 cast

-0.13

 åĽ

-0.13

POSITIVE LOGITS

 îł

0.15

Ã¡genes

0.14

pter

0.14

 tablesp

0.14

Ã©tique

0.14

yonel

0.14

carrier

0.14

ÐŁÐļ

0.14

ayÄ±z

0.13

ervers

0.13

Activations Density 0.023%

references to court-related terminology and legal proceedings

No Comments

No Known Activations