INDEX

Explanations

specific historical artifacts and exhibits related to trains

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

iteur

-0.17

_blocking

-0.16

åħī

-0.15

åľį

-0.15

AIM

-0.14

avar

-0.14

ç©

-0.14

uzzer

-0.14

xfc

-0.14

ctor

-0.13

POSITIVE LOGITS

loc

0.26

 tender

0.25

 Tender

0.23

 Garr

0.21

Loc

0.21

 Steph

0.19

 Compound

0.19

 Pacific

0.19

 Baldwin

0.19

aturated

0.19

Activations Density 0.006%

specific historical artifacts and exhibits related to trains

No Comments

No Known Activations