INDEX

Explanations

technical terms related to programming or data formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

/goto

-0.19

_graphics

-0.15

arkan

-0.15

TECT

-0.14

æı

-0.14

 à¤¦à¤²

-0.14

Î¹Î½

-0.14

 clip

-0.14

æ

-0.14

osc

-0.14

POSITIVE LOGITS

RAW

0.26

 Albums

0.25

 albums

0.24

RAW

0.23

Album

0.23

 Album

0.23

 album

0.22

album

0.21

albums

0.21

ãĤ¢ãĥ«ãĥĲ

0.20

Activations Density 0.083%

technical terms related to programming or data formats

No Comments

No Known Activations