INDEX

Explanations

negative judgments and criticisms related to behavior and ethics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Ð±Ð»Ð°Ð³Ð¾Ð´Ð°ÑĢÑı

-0.19

 thanks

-0.18

 grÃ¢ce

-0.16

thanks

-0.16

lia

-0.15

 nhá»Ŀ

-0.15

unya

-0.14

WithURL

-0.14

 sáºµn

-0.14

Ø§ÙĦÛĮØ§

-0.14

POSITIVE LOGITS

 considering

0.25

 border

0.20

 beyond

0.19

 indeed

0.18

 especially

0.17

to

0.17

border

0.16

 borders

0.15

 behavior

0.15

 Considering

0.15

Activations Density 0.146%

negative judgments and criticisms related to behavior and ethics

No Comments

No Known Activations