INDEX

Explanations

references to specific geographic locations and related organizations

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

sig

-0.17

ibi

-0.15

bsd

-0.15

jer

-0.15

 Î±Ïĥ

-0.14

evi

-0.14

 Lips

-0.14

ÙİÙħ

-0.14

 pont

-0.14

POSITIVE LOGITS

 county

0.28

 County

0.28

shire

0.27

-wide

0.23

hire

0.21

 Const

0.21

 counties

0.20

county

0.20

County

0.20

 Echo

0.19

Activations Density 0.024%

references to specific geographic locations and related organizations

No Comments

No Known Activations