INDEX

Explanations

punctuation marks and associated actions or expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

itches

-0.15

 Merk

-0.14

ittle

-0.13

 Ø¨ÙĪØ§Ø¨Ø©

-0.13

eldom

-0.13

IService

-0.13

Ð½Ð¸Ð²

-0.13

elles

-0.13

nis

-0.13

 Cant

-0.13

POSITIVE LOGITS

Dai

0.15

ayar

0.15

å±Ĭ

0.15

VML

0.14

ãĥĸãĥ«

0.14

(Entity

0.13

erville

0.13

deo

0.13

oret

0.13

mun

0.13

Activations Density 0.016%

punctuation marks and associated actions or expressions

No Comments

No Known Activations