INDEX

Explanations

the use of the word "Sie" and its variations in different grammatical contexts

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

adera

-0.15

iendo

-0.15

asser

-0.15

nek

-0.15

uche

-0.14

raphics

-0.14

Vak

-0.14

chein

-0.14

edException

-0.14

adena

-0.14

POSITIVE LOGITS

gel

0.24

gf

0.22

gent

0.21

zure

0.19

gm

0.19

bert

0.18

ving

0.18

vw

0.17

GF

0.17

bold

0.17

Activations Density 0.006%

the use of the word "Sie" and its variations in different grammatical contexts

No Comments

No Known Activations