INDEX

Explanations

references to legal terms and proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

forman

-0.17

ActionCreators

-0.14

raquo

-0.13

.BLL

-0.13

.bunifuFlatButton

-0.13

ekim

-0.13

ÑĢÐ¾ÑģÑĤÐ¾

-0.13

 ulus

-0.13

ÑĸÑģÐ½Ð¾

-0.12

POSITIVE LOGITS

 Ã¢

0.17

ÃħÅ¸

0.15

 Ãİ

0.15

 whichever

0.13

ÃĤ

0.13

Âħ

0.12

ãĢĤãĢĤ↵↵

0.12

 [âĢ¦]

0.12

Âł↵↵

0.12

ONTAL

0.12

Activations Density 1.387%

references to legal terms and proceedings

No Comments

No Known Activations