INDEX

Explanations

references to the name "Joan" in various contexts and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ensch

-0.19

-0.18

ej

-0.16

vie

-0.15

chai

-0.15

 merchant

-0.15

jav

-0.15

imers

-0.14

alet

-0.14

POSITIVE LOGITS

athan

0.20

 Rivers

0.20

inha

0.19

ildo

0.16

lac

0.15

oven

0.15

_mirror

0.15

uary

0.15

Mirror

0.15

 Mirror

0.15

Activations Density 0.007%

references to the name "Joan" in various contexts and discussions

No Comments

No Known Activations