INDEX

Explanations

programming-related terminology and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Moy

-0.16

oders

-0.15

verture

-0.14

vey

-0.14

 Occupation

-0.14

sold

-0.14

acro

-0.14

nave

-0.14

uo

-0.14

Î¼Î¿Î¯

-0.14

POSITIVE LOGITS

 Revel

0.17

 recip

0.14

ä¹Ī

0.13

(fabs

0.13

eral

0.13

sian

0.13

 Oaks

0.13

cov

0.13

gov

0.13

UME

0.12

Activations Density 0.351%

programming-related terminology and concepts

No Comments

No Known Activations