INDEX

Explanations

fragments of code related to regular expressions and pattern matching

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

esser

-0.16

 marginal

-0.15

urrent

-0.14

Ãł

-0.14

bro

-0.14

ilon

-0.13

uels

-0.13

atÄ±r

-0.13

 serial

-0.13

XA

-0.13

POSITIVE LOGITS

 capture

0.29

 captures

0.28

 Capture

0.28

 captured

0.28

 groups

0.28

Capture

0.27

.group

0.26

 Groups

0.26

captures

0.26

 group

0.25

Activations Density 0.107%

fragments of code related to regular expressions and pattern matching

No Comments

No Known Activations