INDEX

Explanations

references to languages and countries in a given context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oust

-0.16

efe

-0.15

Ø±Ùĩ

-0.15

apt

-0.14

 Carolina

-0.14

.mask

-0.13

uyÃªn

-0.13

file

-0.13

 beard

-0.13

Ú¯Ø§ÙĩÛĮ

-0.13

POSITIVE LOGITS

_IOC

0.16

/stream

0.15

USA

0.15

iyan

0.15

PermissionsResult

0.15

Joi

0.14

ahr

0.14

UNS

0.13

ivos

0.13

Activations Density 0.007%

references to languages and countries in a given context

No Comments

No Known Activations