INDEX

Explanations

structured information and updates regarding events or posts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

jem

-0.16

 Mayer

-0.16

 role

-0.16

ogo

-0.15

kus

-0.15

iane

-0.15

jt

-0.15

Ø§ÙĨÛĮ

-0.15

acho

-0.15

 param

-0.15

POSITIVE LOGITS

emie

0.16

Atoms

0.15

.childNodes

0.14

à¸Ĭà¸²à¸ķ

0.14

SPATH

0.14

pras

0.14

ChildIndex

0.14

ported

0.14

UME

0.14

Activations Density 0.143%

structured information and updates regarding events or posts

No Comments

No Known Activations