INDEX

Explanations

references to legal cases and judicial terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

oric

-0.18

yonel

-0.17

wyn

-0.16

-bot

-0.15

pies

-0.15

golden

-0.14

endon

-0.14

 Stall

-0.14

_Tis

-0.13

 Bott

-0.13

POSITIVE LOGITS

CAM

0.15

 Campos

0.15

nte

0.15

tep

0.14

atory

0.14

 Hanson

0.14

Dot

0.14

 unknown

0.14

aina

0.14

Activations Density 0.159%

references to legal cases and judicial terms

No Comments

No Known Activations