INDEX

Explanations

specific punctuation marks and their frequency in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÑĮ

-0.15

addon

-0.15

earch

-0.15

gos

-0.14

xs

-0.14

SSI

-0.13

hi

-0.13

 Fancy

-0.13

err

-0.13

 Hire

-0.13

POSITIVE LOGITS

%B

0.16

Ã¤ng

0.15

å¡ļ

0.15

ÏģÎº

0.14

laus

0.14

 \č↵

0.14

aken

0.14

 Schultz

0.14

urn

0.14

æĺĩ

0.14

Activations Density 0.056%

specific punctuation marks and their frequency in text

No Comments

No Known Activations