INDEX

Explanations

instances of the word "on."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

dorf

-0.16

addir

-0.15

ugar

-0.15

ÐµÐ¼Ð¾Ð½

-0.15

-git

-0.14

entes

-0.14

 Adoption

-0.14

ä¾

-0.14

anship

-0.14

implicit

-0.13

POSITIVE LOGITS

eger

0.16

 site

0.16

the

0.16

sou

0.15

 Klein

0.15

 technical

0.14

itech

0.14

 manager

0.14

ed

0.14

Activations Density 0.211%

instances of the word "on."

No Comments

No Known Activations