INDEX

Explanations

expressions of appreciation and admiration in personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

soever

-0.15

osi

-0.14

imest

-0.14

/upload

-0.14

essler

-0.13

.infinity

-0.13

arend

-0.13

Ø§ÙĦØ§

-0.13

inery

-0.13

eil

-0.13

POSITIVE LOGITS

how

0.54

how

0.42

 cÃ³mo

0.37

å¦Ĥä½ķ

0.32

 hearing

0.32

HOW

0.30

 seeing

0.30

 ÙĥÙĬÙģ

0.29

 nasÄ±l

0.29

-how

0.27

Activations Density 0.171%

expressions of appreciation and admiration in personal experiences

No Comments

No Known Activations