INDEX

Explanations

references to television series and their elements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ãĥ¼ãĤ¹

-0.17

squeeze

-0.16

Ã¼y

-0.15

 kvinne

-0.15

oleÄį

-0.14

é½

-0.14

FUN

-0.14

 rencont

-0.14

ASP

-0.14

oby

-0.13

POSITIVE LOGITS

agli

0.16

 soap

0.15

cko

0.15

cis

0.15

uxe

0.15

compact

0.15

 Soap

0.15

soap

0.14

lak

0.14

 compact

0.14

Activations Density 0.115%

references to television series and their elements

No Comments

No Known Activations