INDEX

Explanations

mentions of the word "Nag" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 kolo

-0.15

kova

-0.15

ameron

-0.15

phin

-0.14

olars

-0.14

east

-0.14

ABL

-0.14

ilater

-0.13

overs

-0.13

 overs

-0.13

POSITIVE LOGITS

asaki

0.28

oya

0.25

aland

0.25

ourney

0.23

orno

0.22

uib

0.21

ano

0.20

ging

0.19

 Hamm

0.19

pur

0.18

Activations Density 0.007%

mentions of the word "Nag" and its variations

No Comments

No Known Activations