INDEX

Explanations

instances of self-referential relationships or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

:init

-0.16

ixo

-0.16

Ø§Ø¨ÙĬ

-0.15

Ø§Ø¨ÛĮ

-0.14

ÐµÐºÐ°ÑĢ

-0.14

NavController

-0.14

esium

-0.14

_READY

-0.14

oine

-0.14

_TAC

-0.13

POSITIVE LOGITS

 itself

0.52

 themselves

0.48

 himself

0.46

èĩªèº«

0.43

èĩªå·±

0.42

 herself

0.42

 Himself

0.38

own

0.38

 ourselves

0.36

 oneself

0.35

Activations Density 0.231%

instances of self-referential relationships or concepts

No Comments

No Known Activations