INDEX

Explanations

Java or programming-related syntax and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

è¼ª

-0.17

achs

-0.16

eu

-0.15

ousse

-0.15

æīĵ

-0.14

hausen

-0.14

ysz

-0.14

raj

-0.14

itchen

-0.14

estro

-0.14

POSITIVE LOGITS

 movable

0.19

imli

0.18

 nackte

0.17

mpar

0.17

-move

0.16

move

0.16

mov

0.16

ç§»åĭķ

0.15

 move

0.15

&&

0.15

Activations Density 0.003%

Java or programming-related syntax and structures

No Comments

No Known Activations