INDEX

Explanations

references to official orders and government oversight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

TestFixture

-0.15

ostel

-0.15

leton

-0.14

endale

-0.14

gende

-0.14

ãĥ³ãĥĨ

-0.14

unct

-0.13

unes

-0.13

endor

-0.13

 Highway

-0.13

POSITIVE LOGITS

 yesterday

0.16

à¥Įà¤¤

0.14

kop

0.14

ortic

0.14

UID

0.14

Kup

0.14

 Singap

0.14

baÅŁ

0.13

izen

0.13

Activations Density 0.009%

references to official orders and government oversight

No Comments

No Known Activations