INDEX

Explanations

details related to book descriptions, including formats and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Piece

-0.15

Piece

-0.14

MOTE

-0.14

borg

-0.14

aut

-0.14

ipers

-0.14

 Pieces

-0.13

:\/\/

-0.13

POSITIVE LOGITS

pages

0.20

pag

0.20

 pages

0.20

 ÏĥÎµÎ»

0.19

vi

0.19

pag

0.18

pps

0.18

 cloth

0.18

pp

0.17

Pages

0.17

Activations Density 0.050%

details related to book descriptions, including formats and conditions

No Comments

No Known Activations