INDEX

Explanations

technical terms and keywords related to programming and configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

èĪ¬

-0.15

çıŃ

-0.14

/INFO

-0.14

utow

-0.14

sti

-0.14

(()

-0.13

Ð¾Ð²Ð°ÑĢ

-0.13

Ð¾Ð²Ð°ÑĢÐ¸

-0.13

ÑģÐµÐ´

-0.13

sted

-0.13

POSITIVE LOGITS

.go

0.21

spb

0.21

pkg

0.20

internal

0.20

pkg

0.19

util

0.19

pb

0.19

/internal

0.18

htt

0.18

 ioutil

0.17

Activations Density 0.012%

technical terms and keywords related to programming and configuration

No Comments

No Known Activations