INDEX

Explanations

motivational and advisory themes centered around personal growth and community engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Accountability

-0.16

usher

-0.15

enton

-0.15

ullen

-0.15

atcher

-0.15

è

-0.15

 Perkins

-0.14

oom

-0.14

ika

-0.14

adt

-0.13

POSITIVE LOGITS

ourke

0.17

 Reject

0.15

angep

0.14

mav

0.14

oders

0.14

 æĵ

0.14

 yourselves

0.14

è³ª

0.14

Activations Density 0.231%

motivational and advisory themes centered around personal growth and community engagement

No Comments

No Known Activations