INDEX

Explanations

references to collaborative repair activities and skills sharing within a community setting

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

 Shelf

-0.19

gere

-0.16

à¸Īà¸£

-0.15

İ·

-0.14

Ø¹ÙĬ

-0.14

chk

-0.14

tesy

-0.14

rane

-0.13

rego

-0.13

 Glasses

-0.13

POSITIVE LOGITS

 needle

0.38

hem

0.35

 sewing

0.32

sew

0.32

 patch

0.31

 seam

0.31

 needles

0.30

needle

0.29

se

0.29

-se

0.29

Activations Density 0.068%

references to collaborative repair activities and skills sharing within a community setting

No Comments

No Known Activations