INDEX

Explanations

legal terminology and references to judicial proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

OU

-0.18

fone

-0.15

 retro

-0.14

CEPT

-0.14

 Theme

-0.14

SND

-0.14

OU

-0.14

Ìĥ

-0.14

 Capt

-0.14

 Hart

-0.14

POSITIVE LOGITS

 directions

0.21

Directions

0.21

 Directions

0.20

ASIC

0.17

 Crown

0.15

_direction

0.14

 undef

0.14

 corporations

0.14

scheme

0.14

 åıĤ

0.14

Activations Density 0.020%

legal terminology and references to judicial proceedings

No Comments

No Known Activations