INDEX

Explanations

references to game mechanics and teamwork dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Arena

-0.17

imbus

-0.17

Wer

-0.16

baugh

-0.16

bench

-0.15

otron

-0.15

urette

-0.15

.rd

-0.14

imited

-0.14

iske

-0.14

POSITIVE LOGITS

leg

0.20

 Timing

0.18

 Yorker

0.18

leg

0.18

LB

0.17

 york

0.17

 boundaries

0.17

-leg

0.17

 boundary

0.16

 Voll

0.16

Activations Density 0.012%

references to game mechanics and teamwork dynamics

No Comments

No Known Activations