INDEX

Explanations

references to moral and ethical injunctions or transgressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.19

—

-0.17

–

-0.16

ç¸

-0.15

ACHINE

-0.15

 dÃ¼r

-0.15

ÙĬÙĩ

-0.14

_regular

-0.14

eward

-0.14

POSITIVE LOGITS

.scalablytyped

0.17

 tasar

0.17

_tooltip

0.16

tvrt

0.15

 HttpServlet

0.15

pageNum

0.15

Ð¾Ð´ÐµÑĢÐ¶

0.14

ãĤ¤ãĥ¤

0.14

tfoot

0.14

GenerationStrategy

0.14

Activations Density 0.052%

references to moral and ethical injunctions or transgressions

No Comments

No Known Activations