INDEX

Explanations

references to liberalism and related ideologies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

antry

-0.18

jÃŃm

-0.18

anke

-0.17

Î½Î¹

-0.17

orch

-0.16

ean

-0.16

alist

-0.15

onet

-0.15

iers

-0.15

ee

-0.15

POSITIVE LOGITS

ised

0.33

ization

0.32

isation

0.31

ized

0.31

izing

0.29

ize

0.28

ising

0.27

ism

0.27

izes

0.27

ises

0.23

Activations Density 0.022%

references to liberalism and related ideologies

No Comments

No Known Activations