INDEX

Explanations

references to religious seminaries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Î³Î³

-0.19

yp

-0.15

 factor

-0.14

ey

-0.14

uns

-0.14

 jadx

-0.14

 Excellence

-0.13

idders

-0.13

 dabei

-0.13

 unwanted

-0.13

POSITIVE LOGITS

ãĥ¼ãĤº

0.18

isson

0.15

liquid

0.14

åŃ¦éĻ¢

0.14

usercontent

0.14

chein

0.14

zego

0.14

ska

0.14

åĭĻ

0.14

ervo

0.13

Activations Density 0.003%

references to religious seminaries

No Comments

No Known Activations