INDEX

Explanations

occurrences of prepositions and their usage within contexts describing actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

kil

-0.16

soever

-0.16

zelf

-0.15

oppers

-0.15

stead

-0.15

ãģ¤ãģĳ

-0.14

abilia

-0.14

 Ð¿ÑĢÐ¾Ñģ

-0.14

rug

-0.14

POSITIVE LOGITS

/from

0.29

gether

0.29

plevel

0.22

ying

0.19

/about

0.18

ogle

0.18

 lá»Ľn

0.18

tem

0.17

tems

0.17

ledo

0.17

Activations Density 1.653%

occurrences of prepositions and their usage within contexts describing actions or processes

No Comments

No Known Activations