INDEX

Explanations

programming keywords and elements related to coding structures

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

assage

-0.16

_mE

-0.15

atura

-0.15

jvu

-0.15

mas

-0.14

Ã©ry

-0.14

ÎºÎ¿Ïį

-0.14

erdem

-0.14

illance

-0.14

icator

-0.14

POSITIVE LOGITS

 Warren

0.15

Ð¾ÑĢÐ¾

0.14

ello

0.14

.LoggerFactory

0.14

 Input

0.14

 order

0.14

0.13

 truth

0.13

bio

0.13

nes

0.13

Activations Density 0.002%

programming keywords and elements related to coding structures

No Comments

No Known Activations