INDEX

Explanations

programming concepts related to components and rendering logic

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

odash

-0.17

mey

-0.14

 VerfÃ¼gung

-0.14

icket

-0.14

ãĥ¼ãĥĦ

-0.14

ìĪľ

-0.14

rud

-0.13

bic

-0.13

rog

-0.13

esimal

-0.13

POSITIVE LOGITS

vero

0.16

vas

0.15

onda

0.15

 Marvin

0.14

Sez

0.14

otti

0.14

vais

0.14

oad

0.14

ilip

0.14

 focal

0.14

Activations Density 12.632%

programming concepts related to components and rendering logic

No Comments

No Known Activations