INDEX

Explanations

terms related to programming concepts and constructs, particularly those involving adapters and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

á»ĩn

-0.16

Mal

-0.14

ing

-0.14

irs

-0.14

asing

-0.14

 fieldValue

-0.14

rich

-0.14

inj

-0.14

uchen

-0.13

eq

-0.13

POSITIVE LOGITS

Name

0.29

ID

0.28

 name

0.26

_name

0.26

name

0.26

_id

0.26

Id

0.24

 Name

0.23

-name

0.23

åĲįç§°

0.23

Activations Density 0.392%

terms related to programming concepts and constructs, particularly those involving adapters and data structures

No Comments

No Known Activations