INDEX

Explanations

terms related to inclusion and exclusivity

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

utsch

-0.19

eyer

-0.17

hea

-0.17

tsy

-0.16

tember

-0.16

town

-0.15

ieties

-0.15

ever

-0.15

indle

-0.15

elez

-0.15

POSITIVE LOGITS

ions

0.41

ively

0.41

ive

0.40

ional

0.37

iveness

0.37

iÃ³n

0.33

ione

0.29

IVE

0.29

ives

0.28

ivity

0.27

Activations Density 0.045%

terms related to inclusion and exclusivity

No Comments

No Known Activations