INDEX

Explanations

terms related to moral and ethical dilemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

aepernick

-0.16

¼åĲĪ

-0.15

eder

-0.15

aterno

-0.14

/loader

-0.14

-0.13

Ð¬

-0.13

uala

-0.13

iloc

-0.13

nar

-0.13

POSITIVE LOGITS

 exist

1.13

 exists

1.09

 existed

0.99

 existence

0.99

 Exist

0.94

 existing

0.93

exists

0.90

 Exists

0.87

exist

0.86

 existe

0.85

Activations Density 0.354%

terms related to moral and ethical dilemmas

No Comments

No Known Activations