INDEX

Explanations

key programming concepts and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

abee

-0.15

å¢

-0.14

 Herald

-0.14

 Hick

-0.14

 Orth

-0.14

beth

-0.14

entlich

-0.14

VERTISEMENT

-0.14

ying

-0.13

ras

-0.13

POSITIVE LOGITS

aldi

0.15

åĳ

0.14

áº¬

0.14

ogan

0.14

á»ĵng

0.14

yat

0.14

inqu

0.13

¢åįķ

0.13

LOSE

0.13

Activations Density 0.010%

key programming concepts and terminology

No Comments

No Known Activations