INDEX

Explanations

expressions of personal experience and introspection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

seen

-0.16

 barley

-0.15

bout

-0.15

elige

-0.14

ounge

-0.14

Ð½ÑĮÐ¾

-0.14

utin

-0.14

ognition

-0.14

apg

-0.14

 Enlight

-0.14

POSITIVE LOGITS

 suspect

0.21

dim

0.18

Sus

0.17

annis

0.17

 worry

0.17

 increasingly

0.17

 privilege

0.17

lux

0.17

 habit

0.16

 contextual

0.16

Activations Density 0.420%

expressions of personal experience and introspection

No Comments

No Known Activations