INDEX

Explanations

terms related to legal issues or violations

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

atron

-0.17

shaw

-0.15

Mahon

-0.15

iec

-0.14

igne

-0.14

fone

-0.14

æĭĽèģĺ

-0.14

AGMA

-0.14

ause

-0.14

akh

-0.14

POSITIVE LOGITS

 plates

0.35

 plate

0.35

Plate

0.30

 Plate

0.30

plates

0.30

 Plates

0.29

plate

0.27

DM

0.25

tit

0.24

 title

0.21

Activations Density 0.010%

terms related to legal issues or violations

No Comments

No Known Activations