INDEX

Explanations

expressions of love and positive virtues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ispecies

-0.17

 Ø¬Ø§

-0.15

 Ulus

-0.15

ãĥ¼ãĤ

-0.15

Ð¾Ð»Ð¾

-0.14

stroke

-0.14

ouver

-0.14

usalem

-0.14

ãĥģãĥ¥

-0.14

Ð²Ð¸

-0.13

POSITIVE LOGITS

RunWith

0.16

iqueta

0.16

 Gand

0.15

 Quar

0.15

.GetBytes

0.15

ucker

0.14

 Paul

0.14

 Wend

0.14

Paul

0.14

apos

0.14

Activations Density 0.103%

expressions of love and positive virtues

No Comments

No Known Activations