INDEX

Explanations

terms related to representation and advocacy for various groups or communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

orsi

-0.16

hana

-0.15

entes

-0.15

aub

-0.14

_tunnel

-0.14

uhn

-0.14

 classNames

-0.14

engin

-0.14

iert

-0.14

ADE

-0.13

POSITIVE LOGITS

hton

0.16

é³

0.14

stÃ¥

0.14

.scalablytyped

0.14

 Lind

0.14

stood

0.13

ä¾Ĩ

0.13

Ã¹

0.13

 Represent

0.13

Activations Density 0.087%

terms related to representation and advocacy for various groups or communities

No Comments

No Known Activations