INDEX

Explanations

actions related to participation, involvement, and ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ullo

-0.17

autÃ©

-0.15

emble

-0.15

orelease

-0.15

ÑĤÐ¾ÑĢ

-0.14

atform

-0.14

documentation

-0.14

icari

-0.14

forum

-0.14

 Down

-0.14

POSITIVE LOGITS

 forward

0.24

 part

0.22

 receipt

0.20

-forward

0.18

 forwards

0.18

forward

0.18

 possession

0.17

 FORWARD

0.17

 Forward

0.17

 delivery

0.16

Activations Density 0.048%

actions related to participation, involvement, and ownership

No Comments

No Known Activations