INDEX

Explanations

technical terms and data structures related to programming and computer science

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

IBE

-0.15

ÙĦÙĬØ©

-0.15

entes

-0.14

#__

-0.14

 corner

-0.14

Init

-0.13

.sul

-0.13

Î¯Î½Î±

-0.13

ISK

-0.13

ume

-0.13

POSITIVE LOGITS

oya

0.19

oir

0.15

oyo

0.14

ãģĿãģĵ

0.14

 Slut

0.13

Pai

0.13

ska

0.13

 Laden

0.13

 corresponding

0.13

Activations Density 0.259%

technical terms and data structures related to programming and computer science

No Comments

No Known Activations