INDEX

Explanations

programming-related keywords and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ject

-0.17

zia

-0.16

EEP

-0.14

Muj

-0.14

Î¿ÏĤ

-0.14

Ã¡ty

-0.14

udy

-0.14

osis

-0.13

isine

-0.13

POSITIVE LOGITS

adoo

0.17

ç±

0.16

UserCode

0.15

crest

0.15

 Holl

0.15

olean

0.15

iddy

0.14

Meteor

0.14

.activ

0.14

ivet

0.14

Activations Density 0.002%

programming-related keywords and concepts

No Comments

No Known Activations