INDEX

Explanations

instances of text related to post entries in a blog or publication

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

azzo

-0.17

EMPLARY

-0.16

quia

-0.15

 Slack

-0.15

fried

-0.15

bane

-0.14

angel

-0.14

ajo

-0.14

ija

-0.14

estar

-0.14

POSITIVE LOGITS

adera

0.16

éĸĵ

0.14

 Beans

0.14

 acompan

0.14

amespace

0.14

ë¶

0.13

.FileReader

0.13

PUR

0.13

sb

0.13

gesi

0.13

Activations Density 0.002%

instances of text related to post entries in a blog or publication

No Comments

No Known Activations