INDEX

Explanations

programming keywords and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

à¥Ĥà¤²

-0.14

arkin

-0.14

icens

-0.14

pany

-0.14

ÄįÃ¡st

-0.13

IsEmpty

-0.13

 ê·¸ëŁ°

-0.13

ÑģÐ»

-0.13

asil

-0.13

uÄį

-0.13

POSITIVE LOGITS

 ()=>

0.17

 ()=>{↵

0.16

kie

0.16

bz

0.14

 saison

0.14

ennie

0.13

Į¨

0.13

bet

0.13

ogle

0.13

Activations Density 0.126%

programming keywords and constructs

No Comments

No Known Activations