INDEX

Explanations

legal terms and references to jurisdiction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

unkt

-0.15

etten

-0.15

åĭ¢

-0.14

Ð´Ð°ÑĤ

-0.14

stup

-0.14

blo

-0.14

otten

-0.14

çĢ¬

-0.14

ÐµÐºÑĤÐ¸Ð²

-0.14

foy

-0.14

POSITIVE LOGITS

 final

0.15

(Method

0.15

anja

0.15

ifr

0.14

 terms

0.14

 ÎľÎ·

0.14

zap

0.14

 FINAL

0.14

ene

0.13

Activations Density 0.080%

legal terms and references to jurisdiction

No Comments

No Known Activations