INDEX

Explanations

numerical data or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.17

etty

-0.16

osit

-0.16

.promise

-0.15

ahrung

-0.15

pliers

-0.15

yne

-0.14

ienes

-0.13

anggal

-0.13

POSITIVE LOGITS

?>č↵

0.17

oya

0.16

 Pros

0.15

ALLED

0.15

/GPL

0.15

âĸį

0.14

 DateTimeKind

0.14

Ð¼ÑĸÐ½Ñĸ

0.14

Insensitive

0.14

.bp

0.14

Activations Density 0.006%

numerical data or measurements

No Comments

No Known Activations