INDEX

Explanations

characters engaging in social activities or interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 standing

-0.17

 walking

-0.17

 Standing

-0.16

 kneeling

-0.16

 crawling

-0.15

 spont

-0.15

walking

-0.15

 walk

-0.14

æĹħè¡Į

-0.14

 walks

-0.14

POSITIVE LOGITS

tw

0.21

 absorbed

0.20

 absorption

0.20

 leaf

0.19

Abs

0.18

 drum

0.18

leaf

0.18

adm

0.18

 pont

0.18

watch

0.17

Activations Density 0.336%

characters engaging in social activities or interactions

No Comments

No Known Activations