INDEX

Explanations

articles and prepositions in various contexts

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

mpr

-0.14

ansson

-0.14

bject

-0.13

ebek

-0.13

iven

-0.13

phy

-0.13

nem

-0.13

à¥ĩà¤¦à¤¨

-0.13

ipay

-0.12

eless

-0.12

POSITIVE LOGITS

.dm

0.15

.vm

0.14

 Prostit

0.13

 Readonly

0.13

cel

0.13

ure

0.13

&nbsp

0.13

adia

0.13

>NN

0.13

Activations Density 1.505%

articles and prepositions in various contexts

No Comments

No Known Activations