INDEX

Explanations

prepositions indicating relationships and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

semble

-0.19

etheless

-0.18

owed

-0.18

olated

-0.17

jure

-0.17

bestos

-0.17

wards

-0.16

linear

-0.16

gether

-0.16

chÃ©

-0.16

POSITIVE LOGITS

eur

0.18

ffee

0.15

tring

0.15

ering

0.15

oppel

0.14

ection

0.14

ness

0.14

alette

0.14

ea

0.14

atio

0.14

Activations Density 0.236%

prepositions indicating relationships and actions

No Comments

No Known Activations