INDEX

Explanations

phrases related to restrictions and conditions in social or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

actice

-0.15

rish

-0.15

kses

-0.14

reme

-0.14

vys

-0.14

ÏĩÎµÎ¹

-0.14

##_

-0.13

anny

-0.13

.createClass

-0.13

rus

-0.13

POSITIVE LOGITS

uw

0.14

ibal

0.13

cÃŃ

0.13

Door

0.13

ÄŁan

0.13

nez

0.13

stor

0.13

door

0.13

ATUS

0.13

tah

0.13

Activations Density 0.190%

phrases related to restrictions and conditions in social or legal contexts

No Comments

No Known Activations