INDEX

Explanations

references to family relationships and notable individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 person

-0.15

ÏĦÎ¹Î½

-0.15

actories

-0.14

ilde

-0.14

acher

-0.13

 Person

-0.13

 naked

-0.13

 Personen

-0.13

Person

-0.13

tons

-0.13

POSITIVE LOGITS

marvin

0.18

Ã¼rk

0.17

aus

0.15

.mvp

0.14

WithMany

0.13

 Sanity

0.13

eco

0.13

 ÐľÐ°ÑĢÐ¸

0.13

LIC

0.13

rage

0.13

Activations Density 0.208%

references to family relationships and notable individuals

No Comments

No Known Activations