INDEX

Explanations

numerical values and mathematical notations

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

/INFO

-0.16

ellas

-0.15

.mods

-0.15

emma

-0.15

gebra

-0.15

rouch

-0.15

ektor

-0.14

Ã¨ge

-0.14

.identity

-0.14

ÙĬÙĦØ§

-0.14

POSITIVE LOGITS

/+

0.19

/-

0.17

uster

0.16

amon

0.15

agation

0.15

 syll

0.15

(-

0.15

 sign

0.14

err

0.14

 unit

0.14

Activations Density 0.068%

numerical values and mathematical notations

No Comments

No Known Activations