INDEX

Explanations

numerical sequences or patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.17

ãģ£

-0.15

 REGION

-0.15

 Region

-0.15

 aspect

-0.14

/cms

-0.13

ical

-0.13

 chaotic

-0.13

 region

-0.13

POSITIVE LOGITS

rdr

0.16

ADIO

0.16

utron

0.15

enge

0.15

otify

0.15

ldre

0.15

etc

0.14

 DISCLAIMER

0.14

à¹ĩà¸Ķ

0.14

amm

0.14

Activations Density 0.006%

numerical sequences or patterns

No Comments

No Known Activations