INDEX

Explanations

terms related to communication and community

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

aban

-0.15

ãĥ¬ãĥĥãĥĪ

-0.15

nten

-0.14

beit

-0.14

ycin

-0.14

VD

-0.14

bage

-0.14

 Burnett

-0.14

åĳ½

-0.14

POSITIVE LOGITS

wealth

0.28

iquÃ©

0.22

unist

0.21

unal

0.20

orative

0.19

unities

0.18

union

0.18

 comm

0.18

 Comm

0.18

alist

0.18

Activations Density 0.022%

terms related to communication and community

No Comments

No Known Activations