INDEX

Explanations

mentions of the name "Karen" and variations of "Karen" across different contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

guard

-0.17

amina

-0.17

gear

-0.16

eon

-0.16

eric

-0.16

kick

-0.15

utow

-0.15

erior

-0.15

ilip

-0.15

cott

-0.15

POSITIVE LOGITS

ospace

0.18

aken

0.17

 Demir

0.16

itan

0.15

åłĤ

0.15

 Seit

0.15

0.14

egie

0.14

jit

0.14

ismo

0.14

Activations Density 0.006%

mentions of the name "Karen" and variations of "Karen" across different contexts

No Comments

No Known Activations