INDEX

Explanations

references to solo performances or solitary experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

rea

-0.18

wald

-0.17

ted

-0.17

rese

-0.17

rine

-0.16

-ÑĤÐ¾

-0.16

intree

-0.16

olini

-0.15

 Gors

-0.15

zk

-0.15

POSITIVE LOGITS

/single

0.24

ists

0.24

istic

0.22

istically

0.22

 baÅŁÄ±na

0.21

 ranger

0.21

ist

0.20

 wolf

0.20

ISTS

0.18

/group

0.17

Activations Density 0.033%

references to solo performances or solitary experiences

No Comments

No Known Activations