INDEX

Explanations

terminology related to gaming mechanics and strategies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 haus

-0.15

omik

-0.15

æ»ĳ

-0.15

 knobs

-0.15

 gent

-0.14

Ð¾ÑĤÐ¾ÑĢ

-0.14

|:

-0.14

æ£Ĵ

-0.14

Ø±ÛĮØ§ÙĨ

-0.14

/il

-0.13

POSITIVE LOGITS

 enemies

0.20

mob

0.18

 boss

0.18

boss

0.18

mob

0.18

 revive

0.17

ag

0.17

 revived

0.17

 enemy

0.17

 deaths

0.17

Activations Density 0.372%

terminology related to gaming mechanics and strategies

No Comments

No Known Activations