INDEX

Explanations

elements indicating the addition or inclusion of new features or content

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

alsy

-0.17

WithIdentifier

-0.15

phia

-0.14

agram

-0.14

åĲ«

-0.14

gili

-0.14

abcdefghijkl

-0.14

icas

-0.14

Ã¼re

-0.14

 ØµØ§Ø¯

-0.14

POSITIVE LOGITS

 onto

0.49

onto

0.39

 into

0.36

into

0.31

_into

0.27

 vÃło

0.27

Into

0.26

Ont

0.26

 Into

0.25

 INTO

0.24

Activations Density 0.144%

elements indicating the addition or inclusion of new features or content

No Comments

No Known Activations