INDEX

Explanations

actions related to social behavior and appearance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

aise

-0.17

Ã¼t

-0.16

Î»Î¹Îº

-0.15

achen

-0.15

akin

-0.15

 NavParams

-0.14

amed

-0.14

 writ

-0.13

agna

-0.13

POSITIVE LOGITS

eriod

0.16

 differently

0.16

entar

0.15

tracks

0.15

.xticks

0.15

enance

0.14

/rfc

0.13

/cop

0.13

Ð°Ð·Ð°

0.13

edicine

0.13

Activations Density 0.158%

actions related to social behavior and appearance

No Comments

No Known Activations