INDEX

Explanations

references to specific individuals and organizations, particularly within a political or societal context

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

ej

-0.19

incinn

-0.18

loan

-0.15

aggio

-0.15

loe

-0.14

am

-0.14

ÅĻeh

-0.14

lier

-0.14

liers

-0.14

igham

-0.14

POSITIVE LOGITS

uxtap

0.22

stice

0.19

igsaw

0.19

venile

0.17

ÅĽli

0.17

oints

0.16

ST

0.15

ET

0.15

affe

0.15

uggling

0.15

Activations Density 0.838%

references to specific individuals and organizations, particularly within a political or societal context

No Comments

No Known Activations