INDEX

Explanations

elements related to relaxation or calming effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.18

anger

-0.17

 README

-0.15

 Christian

-0.15

 Landing

-0.15

Hoe

-0.15

 Silver

-0.14

 sept

-0.14

 Maint

-0.14

POSITIVE LOGITS

ientos

0.16

actionDate

0.15

croft

0.15

 TÃ¢n

0.15

olik

0.15

pyx

0.14

Ð»Ð°Ð²

0.14

CHIP

0.14

 Budd

0.14

ODULE

0.14

Activations Density 0.095%

elements related to relaxation or calming effects

No Comments

No Known Activations