INDEX

Explanations

dialogue exchanges that express emotional responses or personal interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ÎºÏĮ

-0.16

issen

-0.15

afx

-0.15

 Inner

-0.15

 glGetUniformLocation

-0.14

jev

-0.14

adele

-0.14

xda

-0.14

eos

-0.14

 hist

-0.13

POSITIVE LOGITS

 Toro

0.16

taire

0.15

iddi

0.14

'~/

0.14

ause

0.14

Tor

0.14

ÑĤÐ¾ÑĢ

0.14

çŁ¢

0.13

enor

0.13

 Accord

0.13

Activations Density 0.497%

dialogue exchanges that express emotional responses or personal interactions

No Comments

No Known Activations