INDEX

Explanations

references to personal agency and self-empowerment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ellt

-0.17

idlo

-0.16

annis

-0.15

Ð¾Ð²Ð°ÑĢ

-0.15

ynamo

-0.15

ebo

-0.15

dÃ¼k

-0.15

kok

-0.14

annels

-0.14

.Elapsed

-0.14

POSITIVE LOGITS

 soft

0.19

 Soft

0.18

 soften

0.16

Mac

0.16

 Hard

0.16

Ã¡z

0.15

 William

0.15

 Andres

0.15

Soft

0.15

 hard

0.15

Activations Density 0.029%

references to personal agency and self-empowerment

No Comments

No Known Activations