INDEX

Explanations

references to significant people, places, or events in history

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

_mD

-0.20

_phys

-0.15

eza

-0.15

dÃ¼l

-0.15

_traits

-0.14

phis

-0.14

elop

-0.13

è²¸

-0.13

ylim

-0.13

XL

-0.13

POSITIVE LOGITS

 lucr

0.15

ipro

0.14

etta

0.14

ene

0.14

ìķ½

0.14

adolu

0.14

ayd

0.14

ÐºÑĸ

0.13

alo

0.13

zb

0.13

Activations Density 0.512%

references to significant people, places, or events in history

No Comments

No Known Activations