INDEX

Explanations

plural noun forms and quantifiers

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

appers

-0.17

Ð²ÐµÑĢÐ´

-0.15

 luder

-0.15

 Clifford

-0.14

flate

-0.14

åļ

-0.14

raid

-0.14

idual

-0.14

 à¤

-0.14

.LA

-0.14

POSITIVE LOGITS

assy

0.28

ensual

0.27

uede

0.23

atin

0.22

educt

0.20

izzling

0.20

weet

0.20

ensi

0.19

odash

0.19

velte

0.19

Activations Density 0.028%

plural noun forms and quantifiers

No Comments

No Known Activations