INDEX

Explanations

references to universal or general conditions that apply at all times or anywhere

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

afa

-0.15

orsch

-0.14

oref

-0.14

 dolu

-0.14

_KIND

-0.13

uyo

-0.13

 ÙģØ§Ø±

-0.13

ssl

-0.13

å°¾

-0.13

agram

-0.13

POSITIVE LOGITS

 times

0.35

jun

0.33

 points

0.32

 point

0.27

 moments

0.26

 Points

0.25

points

0.24

 cost

0.23

 intervals

0.23

 given

0.23

Activations Density 0.052%

references to universal or general conditions that apply at all times or anywhere

No Comments

No Known Activations