INDEX

Explanations

references to theatrical productions and performances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

osten

-0.15

criptor

-0.15

 Filme

-0.14

 films

-0.14

 Screen

-0.14

 screen

-0.14

SCREEN

-0.14

 trÃº

-0.14

amas

-0.13

Ð¾Ð¶

-0.13

POSITIVE LOGITS

 productions

0.21

 Productions

0.17

çŃĭ

0.17

 Produ

0.16

 Theatre

0.16

 production

0.16

 theatre

0.16

 staging

0.15

.vars

0.15

 Production

0.15

Activations Density 0.048%

references to theatrical productions and performances

No Comments

No Known Activations