INDEX

Explanations

language related to self-reflection and personal feelings or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 ÑģÐ¾Ðº

-0.15

<quote

-0.15

iaux

-0.15

boss

-0.15

intelligence

-0.15

ROLS

-0.14

.scalablytyped

-0.14

ounce

-0.14

 FindObjectOfType

-0.14

POSITIVE LOGITS

andid

0.17

sac

0.15

-from

0.14

osg

0.14

ama

0.14

ion

0.14

 shop

0.14

med

0.14

ynn

0.14

-widgets

0.14

Activations Density 0.203%

language related to self-reflection and personal feelings or experiences

No Comments

No Known Activations