INDEX

Explanations

mentions of individuals or groups of people in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

clude

-0.14

 ning

-0.14

Ã¶z

-0.14

 something

-0.14

isode

-0.14

åħ¶ä¸Ń

-0.13

agus

-0.13

makt

-0.13

ssf

-0.13

Ãªtes

-0.13

POSITIVE LOGITS

who

0.31

 everywhere

0.30

who

0.25

 worldwide

0.21

 across

0.21

Who

0.18

 Everywhere

0.18

Who

0.18

 whose

0.17

ino

0.16

Activations Density 0.296%

mentions of individuals or groups of people in various contexts

No Comments

No Known Activations