INDEX

Explanations

terms related to gaming mechanics and community features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 audience

-0.25

 Audience

-0.20

 audiences

-0.19

attendance

-0.17

ackets

-0.17

 attendance

-0.17

 Attend

-0.17

 attendee

-0.16

 listener

-0.16

ÑĤÑĢÐ¾Ð½

-0.16

POSITIVE LOGITS

rede

0.15

Tasks

0.15

Peg

0.14

Bon

0.14

 solver

0.14

_prefix

0.14

 Mystery

0.14

inn

0.14

 Crime

0.13

avi

0.13

Activations Density 0.021%

terms related to gaming mechanics and community features

No Comments

No Known Activations