INDEX

Explanations

phrases related to government guidance and legislative documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

anos

-0.19

æª

-0.15

ural

-0.15

ãģĹãģĭ

-0.15

entr

-0.15

cul

-0.15

-0.14

peg

-0.14

å¤®

-0.14

POSITIVE LOGITS

 recent

0.21

recent

0.19

 Recent

0.18

 recently

0.18

yme

0.17

 clients

0.16

_recent

0.16

 CLIENT

0.15

Recent

0.15

 Recently

0.15

Activations Density 0.116%

phrases related to government guidance and legislative documents

No Comments

No Known Activations

phrases related to government guidance and legislative documents

No Comments

No Known Activations