INDEX

Explanations

references to the Northwestern region

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

akin

-0.18

æµħ

-0.15

eworld

-0.14

asso

-0.14

unicorn

-0.14

Ð°ÑĩÐµ

-0.14

allback

-0.14

pler

-0.14

ala

-0.14

POSITIVE LOGITS

 corner

0.23

-corner

0.20

corner

0.18

 Territories

0.18

ern

0.17

PAL

0.17

en

0.16

 corners

0.16

enet

0.16

 comer

0.15

Activations Density 0.015%

references to the Northwestern region

No Comments

No Known Activations