INDEX

Explanations

references to external sources or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ness

-0.17

uncios

-0.16

 mere

-0.15

pa

-0.15

 dissect

-0.14

unner

-0.14

pcodes

-0.14

elerik

-0.14

errupt

-0.14

/provider

-0.14

POSITIVE LOGITS

 below

0.19

 cref

0.16

åľ

0.16

ÄĻÅ¼

0.15

ReuseIdentifier

0.15

#__

0.14

htar

0.14

ings

0.14

 also

0.13

leich

0.13

Activations Density 0.025%

references to external sources or citations

No Comments

No Known Activations