INDEX

Explanations

references to physical assembly and placement of objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Conversion

-0.15

 designs

-0.14

Conversion

-0.14

 Glover

-0.14

 Repair

-0.14

 conversion

-0.14

aho

-0.14

æ»ħ

-0.13

pte

-0.13

anas

-0.13

POSITIVE LOGITS

 placement

0.40

 insertion

0.34

 installation

0.33

 placements

0.31

placement

0.31

 install

0.30

 Placement

0.30

Placement

0.30

 place

0.30

insert

0.29

Activations Density 0.275%

references to physical assembly and placement of objects

No Comments

No Known Activations