INDEX

Explanations

terms related to political ideologies, particularly focusing on liberalism and conservatism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ose

-0.19

jee

-0.17

ee

-0.16

ings

-0.16

antry

-0.15

ocab

-0.15

rei

-0.14

çī©

-0.14

è¡Ŀ

-0.14

ï¸

-0.14

POSITIVE LOGITS

-leaning

0.29

/lib

0.25

/left

0.24

 leaning

0.22

ism

0.19

ized

0.19

ising

0.18

ised

0.18

izing

0.18

ization

0.18

Activations Density 0.025%

terms related to political ideologies, particularly focusing on liberalism and conservatism

No Comments

No Known Activations