INDEX

Explanations

references to Budapest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

stÃ¥

-0.17

ario

-0.16

ial

-0.15

pert

-0.15

eshire

-0.14

iangle

-0.14

allery

-0.14

 bert

-0.14

 exile

-0.13

POSITIVE LOGITS

apest

0.29

ovice

0.19

bud

0.17

hist

0.17

olic

0.17

Bud

0.17

ges

0.16

eto

0.15

enko

0.15

weis

0.15

Activations Density 0.007%

references to Budapest

No Comments

No Known Activations