INDEX

Explanations

references to historical and societal critiques, particularly in relation to issues of oppression or unethical practices

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

Bias

-0.16

 intrig

-0.16

bias

-0.15

/welcome

-0.15

Spo

-0.15

 Bias

-0.15

ussen

-0.14

istani

-0.14

 biased

-0.14

à¹Īà¸²

-0.14

POSITIVE LOGITS

 demon

0.25

 romantic

0.25

 lion

0.24

 commod

0.23

 glam

0.23

å¦ĸ

0.23

 trivial

0.22

 valor

0.22

 normal

0.22

 NORMAL

0.22

Activations Density 0.172%

references to historical and societal critiques, particularly in relation to issues of oppression or unethical practices

No Comments

No Known Activations