INDEX

Explanations

grammatical terms and structures related to adjectives

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

arias

-0.16

(||

-0.16

etti

-0.15

 Bren

-0.15

otics

-0.14

lint

-0.14

 Rock

-0.14

etto

-0.14

gis

-0.14

å¹ķ

-0.14

POSITIVE LOGITS

 morph

0.32

morph

0.29

 Morph

0.28

 morphology

0.27

omor

0.23

 productivity

0.21

 Ð¼Ð¾ÑĢ

0.20

mor

0.20

Mor

0.18

 productive

0.18

Activations Density 0.030%

grammatical terms and structures related to adjectives

No Comments

No Known Activations