INDEX

Explanations

regular expressions and validation formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lico

-0.15

.undefined

-0.15

ÄįÃŃ

-0.14

Ø§Øº

-0.14

ÑĥÑĪ

-0.14

.TextAlignment

-0.13

beck

-0.13

 Redemption

-0.13

PELL

-0.13

RootElement

-0.13

POSITIVE LOGITS

 Pattern

0.34

 pattern

0.33

Pattern

0.30

pattern

0.30

 matches

0.29

 match

0.29

 Match

0.28

 Matcher

0.27

 Matches

0.27

 patterns

0.27

Activations Density 0.128%

regular expressions and validation formats

No Comments

No Known Activations