INDEX

Explanations

references to specific individuals, particularly those named Antonio or 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

æŀľ

-0.18

ewood

-0.17

çİĩ

-0.17

hetto

-0.16

illard

-0.16

fÃ¼g

-0.16

ÑĩÐ°ÑĤ

-0.16

Ð°Ð»ÐµÐ¶

-0.16

tring

-0.15

arton

-0.15

POSITIVE LOGITS

icrobial

0.20

elope

0.20

ipation

0.18

eced

0.17

uario

0.17

uitive

0.16

ecess

0.16

iet

0.15

onyms

0.15

onio

0.15

Activations Density 0.041%

references to specific individuals, particularly those named Antonio or related terms

No Comments

No Known Activations