INDEX

Explanations

variations and adaptations of characters or concepts

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

haus

-0.16

linger

-0.14

ayer

-0.14

elian

-0.14

 Nations

-0.14

ÑĢÐµÐ¹

-0.14

hack

-0.14

à¸²à¸Ķ

-0.14

eria

-0.14

POSITIVE LOGITS

 version

0.16

 Version

0.16

adam

0.16

 versions

0.15

 versiÃ³n

0.15

Version

0.14

jec

0.14

nez

0.14

version

0.14

enis

0.14

Activations Density 0.261%

variations and adaptations of characters or concepts

No Comments

No Known Activations