INDEX

Explanations

punctuation marks and their frequency in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rema

-0.16

åªĴ

-0.15

 EXEMPLARY

-0.15

uu

-0.14

ailable

-0.14

coon

-0.14

Ã¨s

-0.14

fav

-0.14

sek

-0.13

iego

-0.13

POSITIVE LOGITS

 âĨĵ

0.14

 Bones

0.14

ihan

0.14

umbing

0.14

eer

0.13

erties

0.13

ulumi

0.13

Ð°Ð½Ð¾Ð²

0.13

.githubusercontent

0.13

.CodeAnalysis

0.13

Activations Density 0.005%

punctuation marks and their frequency in the text

No Comments

No Known Activations