INDEX

Explanations

references to specific media outlets or publications

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

_nome

-0.17

 POSSIBILITY

-0.16

Nome

-0.15

Äįet

-0.15

sez

-0.15

Atual

-0.15

 Pessoa

-0.15

Rua

-0.15

 idade

-0.15

dados

-0.15

POSITIVE LOGITS

Hoy

0.23

El

0.21

 Desc

0.20

La

0.20

 Cooper

0.19

 Cole

0.19

 Todo

0.18

 Fund

0.18

 Tray

0.18

 Canal

0.18

Activations Density 0.098%

references to specific media outlets or publications

No Comments

No Known Activations