INDEX

Explanations

references to television soap operas and their associated ratings or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

]={↵

-0.16

Ħĸ

-0.16

 kvinne

-0.15

tmpl

-0.15

utc

-0.15

ãĥ¼ãĤ¹

-0.15

Ã¼y

-0.14

ASP

-0.14

ouro

-0.14

Parcelable

-0.14

POSITIVE LOGITS

tw

0.16

 soap

0.15

compact

0.15

 compact

0.15

cis

0.15

à¸¥à¸²

0.14

.xml

0.14

anka

0.14

rien

0.14

Activations Density 0.062%

references to television soap operas and their associated ratings or themes

No Comments

No Known Activations