INDEX

Explanations

mentions of "Family" and related terms

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

undi

-0.18

moz

-0.17

nem

-0.16

aries

-0.15

å®¶æĹı

-0.14

eton

-0.14

 erotische

-0.14

å¤«äºº

-0.14

lush

-0.14

á»§

-0.14

POSITIVE LOGITS

 friendly

0.24

 Friendly

0.23

friendly

0.22

 Owned

0.21

-friendly

0.21

Friendly

0.20

 owned

0.20

 oriented

0.18

-owned

0.17

owned

0.17

Activations Density 0.021%

mentions of "Family" and related terms

No Comments

No Known Activations