INDEX

Explanations

expressions of self-identity or self-description

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

peare

-0.17

èĽ

-0.15

agn

-0.15

arme

-0.14

.scalablytyped

-0.14

Ã´i

-0.14

ilogy

-0.14

 geschichten

-0.14

 Mein

-0.14

>manual

-0.14

POSITIVE LOGITS

 seeking

0.15

à¸Ńà¸²à¸¢

0.15

ugar

0.14

osity

0.14

Ã½

0.14

ATCH

0.14

 writ

0.14

liv

0.14

an

0.14

Activations Density 0.070%

expressions of self-identity or self-description

No Comments

No Known Activations