INDEX

Explanations

instances of the word "open," particularly in different contexts and forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

igne

-0.18

å§Ĳ

-0.15

 Kemp

-0.15

COPE

-0.14

das

-0.14

FRING

-0.14

 mash

-0.14

 Sherlock

-0.14

IDES

-0.14

eldorf

-0.13

POSITIVE LOGITS

idor

0.20

Ĥæķ°

0.16

pras

0.15

ilda

0.15

erate

0.15

ilage

0.14

ARSE

0.14

ãģ£ãģı

0.14

âĪı

0.14

unga

0.13

Activations Density 0.024%

instances of the word "open," particularly in different contexts and forms

No Comments

No Known Activations