INDEX

Explanations

references to tribals or tribal communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

yi

-0.17

intptr

-0.15

oven

-0.14

venir

-0.14

agna

-0.14

aved

-0.14

ointed

-0.14

seed

-0.13

avity

-0.13

ilde

-0.13

POSITIVE LOGITS

 trib

0.27

utes

0.27

ute

0.23

 Trib

0.23

eca

0.21

bons

0.20

ally

0.20

onacci

0.20

unal

0.19

bles

0.19

Activations Density 0.006%

references to tribals or tribal communities

No Comments

No Known Activations