INDEX

Explanations

questions and statements related to choices and personal values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

isque

-0.17

uess

-0.14

Jag

-0.13

noinspection

-0.13

iac

-0.13

.cgi

-0.13

ëĬĲ

-0.13

=YES

-0.13

itez

-0.13

POSITIVE LOGITS

 cáº§n

0.17

 needed

0.17

 necessary

0.16

 nobody

0.16

Æ°

0.16

 needs

0.15

 Mana

0.15

Äįka

0.15

opsy

0.15

ancia

0.15

Activations Density 0.046%

questions and statements related to choices and personal values

No Comments

No Known Activations