INDEX

Explanations

references to essays, articles, and published works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Pron

-0.14

hip

-0.14

 habit

-0.14

posix

-0.14

 deliveries

-0.13

uv

-0.13

avity

-0.13

 interaction

-0.13

 targeted

-0.13

 Ð½Ð°Ñģ

-0.13

POSITIVE LOGITS

 appearing

0.26

 published

0.26

 publication

0.25

 publish

0.22

published

0.22

 appeared

0.22

publication

0.21

 appears

0.20

 apare

0.20

 inclusion

0.20

Activations Density 0.218%

references to essays, articles, and published works

No Comments

No Known Activations