INDEX

Explanations

phrases related to moral and ethical solutions or judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

.activ

-0.16

WR

-0.15

pson

-0.14

ansi

-0.14

mdir

-0.14

aupt

-0.14

åĭĻ

-0.14

éŀ

-0.14

errick

-0.14

 Î£Î±

-0.13

POSITIVE LOGITS

 accordingly

0.27

 correspond

0.27

 corresponding

0.24

 Correspond

0.20

 Accordingly

0.18

 corres

0.18

 likewise

0.18

 accompanying

0.17

 ÑģÐ¾Ð¾ÑĤÐ²ÐµÑĤÑģÑĤÐ²

0.17

 correspondent

0.16

Activations Density 0.212%

phrases related to moral and ethical solutions or judgments

No Comments

No Known Activations