INDEX

Explanations

acronyms and abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.28

-0.24

-0.22

-0.21

-0.20

strup

-0.19

-0.18

TJ

-0.17

ripp

-0.17

TAB

-0.16

POSITIVE LOGITS

0.44

OI

0.27

0.23

OGRAPH

0.21

OX

0.19

Oi

0.19

OE

0.18

din

0.18

Activations Density 0.038%

acronyms and abbreviations

No Comments

No Known Activations