INDEX

Explanations

references to the name "Fran" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

eum

-0.16

slow

-0.15

 slow

-0.15

æĮģãģ¡

-0.14

Î»Î¬

-0.14

 Citation

-0.14

azu

-0.14

Slow

-0.14

optera

-0.14

 Seas

-0.13

POSITIVE LOGITS

furt

0.23

Ã§ois

0.23

isco

0.22

ÑĨÑĥÐ·

0.22

isc

0.21

ophone

0.21

prix

0.19

olin

0.19

fur

0.17

lite

0.17

Activations Density 0.008%

references to the name "Fran" and its variations

No Comments

No Known Activations