INDEX

Explanations

references to legal or procedural terms and actions

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

å¢ĥ

-0.16

 Rarity

-0.16

otch

-0.15

 mÃ¦nd

-0.15

odv

-0.14

alten

-0.14

&M

-0.13

 Harden

-0.13

ÏĦÎ®ÏĤ

-0.13

exus

-0.13

POSITIVE LOGITS

 Basil

0.20

ÆĴ

0.16

 Opposition

0.16

Fon

0.16

Gam

0.16

 gazet

0.15

Diy

0.15

EP

0.15

MP

0.15

 Geneva

0.15

Activations Density 0.001%

references to legal or procedural terms and actions

No Comments

No Known Activations