INDEX

Explanations

phrases and terms related to moral and ethical dilemmas in various contexts

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

 Â«

-0.17

“

-0.15

DF

-0.15

cur

-0.15

à¤¢

-0.15

df

-0.14

'>$

-0.14

``

-0.14

POSITIVE LOGITS

ÑĢÐµÐ±

0.16

0.14

âĢ¬

0.14

ìĹĩ

0.14

"+"

0.14

TM

0.14

ollectors

0.14

exels

0.13

FRINGEMENT

0.13

”çļĦ

0.13

Activations Density 0.301%

phrases and terms related to moral and ethical dilemmas in various contexts

No Comments

No Known Activations