INDEX

Explanations

specific references to legal and employment-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ertz

-0.22

 Crowley

-0.17

elligent

-0.16

 Barcl

-0.16

amba

-0.16

pac

-0.15

anta

-0.15

.cgi

-0.15

áº¡

-0.14

 straw

-0.14

POSITIVE LOGITS

tfoot

0.17

ovÃŃ

0.15

 Pear

0.15

lo

0.15

enc

0.15

icare

0.15

lov

0.15

ONY

0.14

EntityType

0.14

 Viktor

0.14

Activations Density 0.029%

specific references to legal and employment-related terms

No Comments

No Known Activations