INDEX

Explanations

Boolean logic statements and conditions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

jezd

-0.19

 Nack

-0.16

Nap

-0.15

 Bust

-0.14

horn

-0.14

apan

-0.14

ask

-0.14

 createSelector

-0.14

eners

-0.14

jang

-0.14

POSITIVE LOGITS

atat

0.14

morgan

0.14

imeter

0.14

etur

0.14

ijken

0.13

Slug

0.13

reur

0.13

 scarcely

0.13

cÃ©

0.13

Ã¤nder

0.13

Activations Density 0.079%

Boolean logic statements and conditions in code

No Comments

No Known Activations