INDEX

Explanations

words or suffixes related to "ian" or "ian-related" concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ses

-0.21

ted

-0.19

sar

-0.18

gers

-0.17

tt

-0.17

go

-0.17

gaard

-0.17

tit

-0.16

gie

-0.16

inator

-0.16

POSITIVE LOGITS

apolis

0.31

ism

0.30

alysis

0.28

isme

0.24

ische

0.23

ISM

0.21

thus

0.21

-American

0.20

um

0.20

ismo

0.20

Activations Density 0.074%

words or suffixes related to "ian" or "ian-related" concepts

No Comments

No Known Activations