INDEX

Explanations

code-related terms and structures in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

lict

-0.15

unger

-0.15

hart

-0.14

onen

-0.14

unn

-0.14

ĥĿ

-0.13

ernal

-0.13

onas

-0.13

abad

-0.13

POSITIVE LOGITS

 scala

0.26

 spray

0.26

 cats

0.26

 scal

0.24

 collection

0.22

 akka

0.21

sco

0.21

 _↵

0.20

cats

0.20

 play

0.20

Activations Density 0.006%

code-related terms and structures in programming languages

No Comments

No Known Activations