INDEX

Explanations

numerical ratings or scores

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÑīÐ¸

-0.15

swire

-0.15

andel

-0.15

 Gross

-0.15

 rever

-0.15

 gross

-0.14

cka

-0.14

attery

-0.14

record

-0.14

pr

-0.13

POSITIVE LOGITS

 rating

0.26

Rating

0.26

rating

0.25

 Rating

0.25

_rating

0.24

 score

0.23

-rating

0.22

ratings

0.21

 stars

0.21

 ratings

0.21

Activations Density 0.061%

numerical ratings or scores

No Comments

No Known Activations