INDEX

Explanations

features and qualities of electronic devices

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

 counselors

-0.19

 savory

-0.18

 Counseling

-0.17

 counselor

-0.17

 Coloring

-0.17

 coloring

-0.17

 fiber

-0.17

 signaling

-0.17

 colors

-0.16

 favorites

-0.16

POSITIVE LOGITS

 Â£

0.22

 (Â£

0.21

 Sony

0.19

Son

0.18

UK

0.17

 lump

0.17

'n

0.17

 matt

0.16

’n

0.15

 armour

0.15

Activations Density 0.018%

features and qualities of electronic devices

No Comments

No Known Activations