INDEX

Explanations

programming and coding-related terms and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

.pitch

-0.16

 Sanayi

-0.16

_dll

-0.15

ÐµÐ²Ñĸ

-0.14

unfold

-0.14

Pitch

-0.14

 pulumi

-0.14

gql

-0.14

EATURE

-0.14

jing

-0.14

POSITIVE LOGITS

Spr

0.21

 game

0.20

spr

0.19

 enemies

0.18

 Game

0.17

 Lives

0.17

 curs

0.17

Hud

0.17

 boss

0.17

 Phaser

0.16

Activations Density 0.047%

programming and coding-related terms and constructs

No Comments

No Known Activations