INDEX

Explanations

references to familial or relational connections

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

udic

-0.17

adier

-0.17

Ã¡Äį

-0.16

eldig

-0.16

Ã³nico

-0.16

iáº¿t

-0.15

ajs

-0.15

vÃ©d

-0.15

edik

-0.15

.usermodel

-0.15

POSITIVE LOGITS

0.18

Ī

0.17

La

0.16

 Lance

0.15

Tr

0.15

rance

0.15

 Astronomy

0.15

Br

0.14

La

0.14

Activations Density 0.039%

references to familial or relational connections

No Comments

No Known Activations