INDEX

Explanations

adjectives and their functions in modifying nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

å¹ķ

-0.15

 Ð¿ÑĢÐ¾Ð²

-0.15

cher

-0.14

lint

-0.14

quet

-0.14

 Craw

-0.14

 provid

-0.14

éĨĴ

-0.13

znÃ¡m

-0.13

 Carp

-0.13

POSITIVE LOGITS

 morph

0.25

 morphology

0.25

inf

0.22

morph

0.22

 Morph

0.21

 stems

0.20

 borrow

0.20

aff

0.19

 particle

0.19

 Ð¼Ð¾ÑĢ

0.19

Activations Density 0.032%

adjectives and their functions in modifying nouns

No Comments

No Known Activations