INDEX

Explanations

references to power or related concepts in various contexts, particularly in relation to energy and authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ago

-0.18

sis

-0.17

engo

-0.16

 Manufact

-0.15

wert

-0.15

rows

-0.15

.Localization

-0.14

 stew

-0.14

inger

-0.14

ok

-0.14

POSITIVE LOGITS

fully

0.24

edBy

0.22

 supply

0.20

 power

0.19

ful

0.19

 Power

0.19

FUL

0.18

.Power

0.18

(power

0.17

 outage

0.17

Activations Density 0.023%

references to power or related concepts in various contexts, particularly in relation to energy and authority

No Comments

No Known Activations