INDEX

Explanations

references to specific locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

iendo

-0.16

Ã³nico

-0.16

 Shade

-0.15

uciÃ³n

-0.15

åį

-0.15

ificaciones

-0.14

Ã³m

-0.14

amient

-0.14

unl

-0.14

Hola

-0.14

POSITIVE LOGITS

 Guar

0.25

 Paran

0.24

 Florian

0.24

MG

0.23

 Uber

0.22

 Campos

0.22

Uber

0.22

MG

0.22

Pir

0.21

 Serg

0.21

Activations Density 0.025%

references to specific locations and institutions

No Comments

No Known Activations