INDEX

Explanations

references to historical and geopolitical entities, specifically related to empires and their territories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 karak

-0.16

 Malcolm

-0.15

 nest

-0.15

feld

-0.15

 Nested

-0.14

 nested

-0.14

 shower

-0.14

 nesting

-0.14

iser

-0.13

_nested

-0.13

POSITIVE LOGITS

å½

0.17

akin

0.17

riz

0.15

oundary

0.15

esz

0.14

oulouse

0.14

 Slam

0.14

agli

0.14

ulls

0.14

Activations Density 0.218%

references to historical and geopolitical entities, specifically related to empires and their territories

No Comments

No Known Activations