INDEX

Explanations

instances of the word "use" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ships

-0.17

ship

-0.17

ren

-0.16

pNet

-0.16

rego

-0.15

ly

-0.15

ATUS

-0.15

ross

-0.15

.deb

-0.15

arty

-0.14

POSITIVE LOGITS

fully

0.22

able

0.20

full

0.19

ful

0.18

age

0.17

ableObject

0.16

lessly

0.15

fulness

0.15

fixtures

0.15

childNodes

0.14

Activations Density 0.045%

instances of the word "use" and its variations

No Comments

No Known Activations