INDEX

Explanations

recurring phrases involving "go to" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Opport

-0.15

castle

-0.15

endon

-0.15

 æĬķç¨¿

-0.15

DidLoad

-0.14

borough

-0.14

istant

-0.14

rc

-0.14

Ĩ

-0.14

POSITIVE LOGITS

thic

0.28

go

0.22

lem

0.22

-to

0.22

-go

0.20

vt

0.19

oose

0.19

lemn

0.18

bern

0.17

-To

0.17

Activations Density 0.007%

recurring phrases involving "go to" in various contexts

No Comments

No Known Activations