INDEX

Explanations

numerical references and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ã¼mÃ¼

-0.16

umlu

-0.15

ãĢħ

-0.15

zyst

-0.15

ANNEL

-0.14

ĶĦ

-0.14

uD

-0.14

ldb

-0.14

unga

-0.14

ÆĴ

-0.13

POSITIVE LOGITS

 sayÄ±lÄ±

0.20

mAh

0.19

/QÄĲ

0.18

adia

0.17

ë²Ī

0.16

hrs

0.16

 Ness

0.15

andle

0.15

atically

0.15

-ci

0.14

Activations Density 0.132%

numerical references and identifiers

No Comments

No Known Activations