INDEX

Explanations

references to specific locations and institutions related to conferences and events

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

ungi

-0.17

 Aberdeen

-0.16

abaj

-0.16

resden

-0.16

 mushroom

-0.16

 Dresden

-0.15

Dan

-0.15

berman

-0.14

ukan

-0.14

ogg

-0.14

POSITIVE LOGITS

 limburg

0.25

 Cincinnati

0.22

NR

0.21

Bon

0.21

 Cologne

0.21

Rhe

0.20

 Belgian

0.20

ngx

0.19

Rh

0.18

 Bengals

0.17

Activations Density 0.022%

references to specific locations and institutions related to conferences and events

No Comments

No Known Activations