INDEX

Explanations

discussions about personal health experiences and recovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

vat

-0.15

yle

-0.15

kad

-0.15

ÐµÐ³Ð¾ÑĢ

-0.15

argar

-0.14

nees

-0.14

vine

-0.14

 lead

-0.14

vrier

-0.14

POSITIVE LOGITS

 Wealth

0.16

 Ø¹ÙĦÙĬÙĥ

0.16

 Ð²Ð°Ð¼

0.15

 wealth

0.15

 your

0.15

ëįĶ

0.15

otos

0.15

iesel

0.14

enler

0.14

 Colbert

0.14

Activations Density 0.260%

discussions about personal health experiences and recovery

No Comments

No Known Activations