INDEX

Explanations

references to doors and their functions or interactions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

inerary

-0.17

emia

-0.16

ency

-0.16

Ä±rak

-0.16

aginator

-0.15

opies

-0.14

ucci

-0.14

/Error

-0.14

ching

-0.14

mons

-0.14

POSITIVE LOGITS

-door

0.22

ways

0.18

aleigh

0.17

keeper

0.16

house

0.16

/Gate

0.16

prising

0.16

 doors

0.15

/trunk

0.15

nd

0.15

Activations Density 0.056%

references to doors and their functions or interactions in the text

No Comments

No Known Activations