INDEX

Explanations

mentions of "power" 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

.Emit

-0.16

sis

-0.16

engo

-0.15

RATE

-0.14

 Manufact

-0.14

kelig

-0.14

otte

-0.14

ewire

-0.14

owitz

-0.14

POSITIVE LOGITS

fully

0.28

ful

0.22

(power

0.21

edBy

0.20

.Power

0.20

houses

0.19

 power

0.19

 Power

0.19

 supply

0.18

FUL

0.18

Activations Density 0.030%

mentions of "power" in various contexts

No Comments

No Known Activations