INDEX

Explanations

references to communities and geographic locations

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

 downstairs

-0.15

WARDS

-0.15

entai

-0.15

	inline

-0.14

 Underground

-0.14

 inline

-0.14

.inline

-0.14

inline

-0.14

 Downtown

-0.14

 DateTimeOffset

-0.14

POSITIVE LOGITS

 near

0.53

 outside

0.45

near

0.42

 north

0.40

 northwest

0.39

 northeast

0.39

outside

0.38

 south

0.37

 Near

0.36

 southwest

0.35

Activations Density 0.329%

references to communities and geographic locations

No Comments

No Known Activations