INDEX

Explanations

variations of the root word "im" and related prefixes or suffixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.42

-0.41

mie

-0.29

-0.26

mah

-0.25

pom

-0.24

pel

-0.24

an

-0.23

mux

-0.23

mj

-0.23

POSITIVE LOGITS

0.23

mary

0.21

orphism

0.20

tura

0.19

mm

0.19

ensions

0.19

orphic

0.18

plitude

0.18

tÃ¼

0.18

metry

0.17

Activations Density 0.065%

variations of the root word "im" and related prefixes or suffixes

No Comments

No Known Activations