INDEX

Explanations

elements related to document formatting and indexing operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ã©gor

-0.16

 assort

-0.16

 Swords

-0.15

innacle

-0.15

ower

-0.15

 nackte

-0.15

OWER

-0.15

pai

-0.14

tablet

-0.14

ahlen

-0.14

POSITIVE LOGITS

arem

0.18

Pon

0.16

ech

0.16

alah

0.15

Ist

0.15

 subsection

0.15

 listings

0.14

mik

0.14

-indent

0.14

asl

0.14

Activations Density 0.011%

elements related to document formatting and indexing operations

No Comments

No Known Activations