INDEX

Explanations

opportunities for participation and input in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

erras

-0.17

>(*

-0.15

loh

-0.15

dek

-0.14

 chÃ³ng

-0.14

ematik

-0.14

Î¼Î±

-0.14

uxt

-0.14

 ê³Ħ

-0.13

_quad

-0.13

POSITIVE LOGITS

 express

0.38

express

0.33

 voice

0.33

 expresses

0.33

Express

0.32

 expressing

0.32

 Express

0.30

vo

0.29

 share

0.29

 EXPRESS

0.28

Activations Density 0.186%

opportunities for participation and input in discussions

No Comments

No Known Activations

opportunities for participation and input in discussions

No Comments

No Known Activations