INDEX

Explanations

connections between concepts in a structured or logical manner

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

morph

-0.18

mour

-0.16

fgang

-0.14

edd

-0.14

à¸ģà¸ķ

-0.14

 morph

-0.14

 rumpe

-0.14

 Morph

-0.14

ehler

-0.14

izoph

-0.14

POSITIVE LOGITS

ãĤıãģĳ

0.18

bid

0.17

 bids

0.17

 milit

0.16

 superv

0.16

 condu

0.15

 furn

0.15

 incident

0.15

deg

0.15

 afford

0.15

Activations Density 0.331%

connections between concepts in a structured or logical manner

No Comments

No Known Activations