INDEX

Explanations

references to support, sponsorship, and patronage

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

 coverage

-0.16

anki

-0.15

 Coverage

-0.14

Ð±Ñĭ

-0.14

avras

-0.14

hammad

-0.14

lesi

-0.14

forge

-0.14

 Barg

-0.14

 Weiss

-0.13

POSITIVE LOGITS

 upgrade

0.21

 reserved

0.19

VIP

0.19

 membership

0.19

 tiers

0.19

 Upgrade

0.19

Reserved

0.19

 subscribers

0.18

membership

0.18

 level

0.18

Activations Density 0.096%

references to support, sponsorship, and patronage

No Comments

No Known Activations