INDEX

Explanations

references to geographical locations and outdoor activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Howe

-0.15

/tutorial

-0.14

amba

-0.14

bum

-0.14

zion

-0.14

.crm

-0.14

 SCORE

-0.13

ostat

-0.13

jin

-0.13

kuk

-0.13

POSITIVE LOGITS

 Domain

0.21

 Chem

0.19

IGN

0.19

 Circuit

0.18

 Route

0.18

 municipal

0.17

 Classified

0.17

RD

0.17

Roc

0.17

 domain

0.17

Activations Density 0.136%

references to geographical locations and outdoor activities

No Comments

No Known Activations