INDEX

Explanations

phrases related to morality 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

eyer

-0.17

VERRIDE

-0.16

odon

-0.15

OD

-0.14

zon

-0.14

 Dove

-0.14

adal

-0.14

 Accept

-0.14

.respond

-0.14

 Clear

-0.14

POSITIVE LOGITS

 statement

0.18

 correct

0.17

 statements

0.17

ãĤ¤ãĤº

0.15

correct

0.15

 guts

0.15

pler

0.14

Ð´Ð¶

0.14

ntl

0.14

è¯´çļĦ

0.14

Activations Density 0.349%

phrases related to morality and ethics

No Comments

No Known Activations