INDEX

Explanations

references to notable actors or their achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Pulitzer

-0.17

Rew

-0.15

Touches

-0.15

erer

-0.15

abi

-0.14

 Album

-0.14

 written

-0.14

avid

-0.13

 Revision

-0.13

isNull

-0.13

POSITIVE LOGITS

 actor

0.34

 actors

0.32

 Actors

0.32

 acting

0.31

actor

0.29

 Actor

0.28

Actor

0.27

akt

0.25

 actress

0.25

 Acting

0.25

Activations Density 0.214%

references to notable actors or their achievements

No Comments

No Known Activations