INDEX

Explanations

the word "names" and variations or contexts of the term throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.19

ahn

-0.16

ptal

-0.15

amaz

-0.14

å¥Ī

-0.14

ernaut

-0.14

eshire

-0.13

ÐµÐ»Ð¸Ñĩ

-0.13

-span

-0.13

POSITIVE LOGITS

.xz

0.17

.idea

0.15

ogne

0.14

Ð»Ð¸Ð¼

0.14

LogFile

0.14

æı

0.14

Ã¡zd

0.14

 tumble

0.14

kommen

0.14

-urlencoded

0.14

Activations Density 0.012%

the word "names" and variations or contexts of the term throughout the text

No Comments

No Known Activations