INDEX

Explanations

references to legal codes and procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

iete

-0.17

ipar

-0.14

åįĶ

-0.14

vell

-0.14

iki

-0.14

 Pend

-0.14

br

-0.14

odb

-0.14

itou

-0.13

kv

-0.13

POSITIVE LOGITS

.Code

0.27

 Code

0.25

code

0.23

endcode

0.22

Code

0.22

_Code

0.22

(Code

0.21

 code

0.21

.getCode

0.21

(code

0.20

Activations Density 0.041%

references to legal codes and procedures

No Comments

No Known Activations