INDEX

Explanations

references to specific individuals or family relations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ø²Ùħ

-0.16

ActionCreators

-0.16

buie

-0.15

zbollah

-0.15

aurus

-0.14

aven

-0.14

ØªØ§Ø¨

-0.14

ÂĮ

-0.14

 è¿ĳ

-0.14

 Dane

-0.13

POSITIVE LOGITS

 gene

0.21

gene

0.20

 Gene

0.18

Gene

0.17

 paternal

0.16

DNA

0.15

aft

0.15

gun

0.14

itness

0.14

Activations Density 0.042%

references to specific individuals or family relations

No Comments

No Known Activations