INDEX

Explanations

concepts related to evidence and legal claims

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

deaux

-0.15

fam

-0.15

fed

-0.15

ania

-0.14

Ð¸ÑĤÐµÐ»ÐµÐ¹

-0.14

 feed

-0.14

 knock

-0.14

czy

-0.14

 Nation

-0.14

 prosec

-0.14

POSITIVE LOGITS

 later

0.16

LineNumber

0.15

 record

0.15

enaire

0.15

airo

0.15

-CP

0.15

irma

0.15

 Record

0.14

 retention

0.14

pst

0.14

Activations Density 0.133%

concepts related to evidence and legal claims

No Comments

No Known Activations