INDEX

Explanations

references to actors and their roles in the film industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

abi

-0.16

InputElement

-0.15

iaux

-0.15

ABI

-0.15

elsing

-0.14

à¸ķà¸£

-0.14

Ã³b

-0.14

ÃŃl

-0.14

afort

-0.14

Î»Ïī

-0.13

POSITIVE LOGITS

 actor

0.86

 actors

0.85

 acting

0.81

 Actor

0.76

actor

0.75

 Actors

0.75

Actor

0.69

actors

0.67

 Acting

0.66

 actress

0.65

Activations Density 0.366%

references to actors and their roles in the film industry

No Comments

No Known Activations