INDEX

Explanations

specific brand names or notable entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ince

-0.15

wort

-0.14

omy

-0.14

 epic

-0.14

 season

-0.14

 Handy

-0.14

 Truy

-0.13

ç¬¦

-0.13

 either

-0.13

POSITIVE LOGITS

ÎºÎ¿Ïħ

0.15

 ÑĥÐ»ÑĥÑĩ

0.15

kk

0.14

å¡

0.14

zym

0.14

Äįin

0.14

Å¡k

0.13

aira

0.13

 igen

0.13

Gim

0.13

Activations Density 0.007%

specific brand names or notable entities

No Comments

No Known Activations