INDEX

Explanations

prepositions and conjunctions that indicate relationships between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.17

enou

-0.16

schemas

-0.16

-0.15

iflower

-0.15

fidf

-0.15

mmas

-0.14

ebo

-0.14

isÃŃ

-0.14

POSITIVE LOGITS

sta

0.32

st

0.28

sv

0.25

utom

0.24

ment

0.24

bind

0.23

uts

0.23

vÃ¤

0.22

ber

0.22

vir

0.22

Activations Density 0.011%

prepositions and conjunctions that indicate relationships between concepts

No Comments

No Known Activations