INDEX

Explanations

phrases related to problem-solving and methodological approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

obuf

-0.14

amel

-0.14

caff

-0.14

bid

-0.14

ttl

-0.13

 Äĳá»Ŀi

-0.13

ett

-0.13

ëĭ¹

-0.13

abeth

-0.13

pha

-0.13

POSITIVE LOGITS

avian

0.15

 autogenerated

0.14

usch

0.14

SI

0.14

upplier

0.14

 Haus

0.13

arger

0.13

-independent

0.13

 èĪ

0.13

Activations Density 0.082%

phrases related to problem-solving and methodological approaches

No Comments

No Known Activations