INDEX

Explanations

mentions of actors and their respective roles in movies or shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

arend

-0.16

ÐºÐ¾Ð¿

-0.16

lder

-0.15

tÃŃ

-0.15

DRAW

-0.14

 fecha

-0.14

kup

-0.14

laÄį

-0.14

áº¿

-0.14

DATED

-0.14

POSITIVE LOGITS

ivos

0.14

 å£°

0.13

 agency

0.13

 choice

0.13

 Beacon

0.13

 antid

0.13

bes

0.13

ÙħÙħ

0.13

ponents

0.13

 tongue

0.13

Activations Density 0.054%

mentions of actors and their respective roles in movies or shows

No Comments

No Known Activations