INDEX

Explanations

instances of standing or sitting positions and their variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Sit

-0.21

sit

-0.20

 sitting

-0.18

oci

-0.16

 Sitting

-0.16

Quest

-0.15

 sits

-0.15

å°ĸ

-0.15

Ļ¨

-0.14

 Desc

-0.14

POSITIVE LOGITS

 motion

0.18

 Motion

0.17

.motion

0.17

Motion

0.16

 perfectly

0.15

yor

0.15

 facing

0.15

 RectTransform

0.14

motion

0.14

 next

0.14

Activations Density 0.110%

instances of standing or sitting positions and their variations

No Comments

No Known Activations