INDEX

Explanations

references to various educational subjects and disciplines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

eve

-0.15

Hang

-0.14

¦

-0.14

lez

-0.14

@js

-0.14

tut

-0.14

gue

-0.14

avic

-0.14

.grad

-0.14

idy

-0.13

POSITIVE LOGITS

vez

0.15

olini

0.14

ypass

0.14

åĨĬ

0.14

iani

0.14

vr

0.14

apid

0.14

 department

0.14

WidgetItem

0.13

<<<

0.13

Activations Density 0.043%

references to various educational subjects and disciplines

No Comments

No Known Activations