INDEX

Explanations

instances of text related to written elements or inscriptions

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

èĮĤ

-0.17

esy

-0.15

alette

-0.15

Ð´ÐµÐ¹ÑģÑĤÐ²

-0.15

-0.14

Ð¾Ð»Ð¾Ð¼

-0.14

 Lambert

-0.14

idor

-0.14

elho

-0.14

rai

-0.14

POSITIVE LOGITS

 formations

0.17

ograph

0.15

azor

0.15

 formation

0.15

inz

0.15

aley

0.15

anda

0.14

|required

0.14

 formed

0.14

 chalk

0.14

Activations Density 0.082%

instances of text related to written elements or inscriptions

No Comments

No Known Activations