INDEX

Explanations

adverse descriptors indicating negativity or poor quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ee

-0.16

eb

-0.15

endon

-0.15

dale

-0.15

_maximum

-0.15

cean

-0.14

inz

-0.14

ordial

-0.14

orr

-0.14

ovÃ¡

-0.14

POSITIVE LOGITS

ger

0.34

gers

0.25

-news

0.24

dest

0.23

 luck

0.22

ging

0.22

lands

0.20

GER

0.20

ged

0.19

ges

0.19

Activations Density 0.031%

adverse descriptors indicating negativity or poor quality

No Comments

No Known Activations