INDEX

Explanations

instances of the word "work" and its variations, indicating a focus on effort and productivity

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

 Seks

-0.15

ught

-0.14

ads

-0.14

ÐµÑĢÑĪ

-0.14

 Baldwin

-0.14

#ad

-0.14

elan

-0.14

gone

-0.13

 Herman

-0.13

çŁ¢

-0.13

POSITIVE LOGITS

 harder

0.19

 magic

0.18

magic

0.17

 hardest

0.17

 Magic

0.16

 hard

0.16

åĿĬ

0.16

äººåĵ¡

0.16

Magic

0.15

out

0.15

Activations Density 0.057%

instances of the word "work" and its variations, indicating a focus on effort and productivity

No Comments

No Known Activations