INDEX

Explanations

programming keywords and data structures related to software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

immel

-0.15

apia

-0.15

EMS

-0.14

 otherwise

-0.14

alian

-0.14

nst

-0.14

otherwise

-0.13

ç¸

-0.13

 Otherwise

-0.13

eners

-0.13

POSITIVE LOGITS

soever

0.17

ineTransform

0.15

olute

0.15

clar

0.15

undance

0.15

ilter

0.15

_exempt

0.15

ÑĢÑı

0.15

vala

0.14

felt

0.14

Activations Density 0.246%

programming keywords and data structures related to software development

No Comments

No Known Activations