INDEX

Explanations

mathematical variables and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 gridColumn

-0.16

iola

-0.16

Ã¡genes

-0.15

iam

-0.15

 Pregn

-0.14

arton

-0.14

arity

-0.14

cape

-0.14

raph

-0.14

POSITIVE LOGITS

ameda

0.15

Ð¼Ð¸ÑĢ

0.15

é¦Ĩ

0.15

ej

0.15

bris

0.15

obi

0.14

ienda

0.14

ujet

0.14

ahir

0.14

INGLE

0.14

Activations Density 0.111%

mathematical variables and operations

No Comments

No Known Activations