INDEX

Explanations

phrases related to regulatory frameworks and formal agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÙĪÙĬØ±

-0.15

dic

-0.14

obot

-0.14

inki

-0.14

ahkan

-0.13

strup

-0.13

pler

-0.13

istance

-0.13

ibre

-0.13

 strokeLine

-0.13

POSITIVE LOGITS

äººãģ¯

0.16

urname

0.16

lotte

0.15

åŃĲãģ¯

0.15

0.14

manuel

0.14

Ã¡bado

0.14

UND

0.13

lsen

0.13

Activations Density 1.317%

phrases related to regulatory frameworks and formal agreements

No Comments

No Known Activations