INDEX

Explanations

evaluations and ratings of games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Attend

-0.15

 fucks

-0.14

ÏĢÎ·

-0.14

Fuck

-0.14

PRINTF

-0.14

 attendee

-0.14

attend

-0.14

 fucked

-0.14

 Fuck

-0.13

uba

-0.13

POSITIVE LOGITS

HO

0.21

 game

0.20

Strategy

0.19

morph

0.19

 gameplay

0.19

 Strategy

0.18

 morph

0.18

 Hidden

0.18

 Developers

0.17

 games

0.17

Activations Density 0.002%

evaluations and ratings of games

No Comments

No Known Activations