INDEX

Explanations

mathematical concepts and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ilm

-0.21

ysz

-0.16

-0.15

Ð¸ÑģÐ»Ð¾Ð²

-0.15

 Howe

-0.15

POSITIVE LOGITS

folk

0.17

hear

0.17

lou

0.14

LastError

0.14

.about

0.14

loff

0.14

fak

0.14

ampa

0.13

nard

0.13

ampo

0.13

Activations Density 0.102%

mathematical concepts and symbols

No Comments

No Known Activations