INDEX

Explanations

words and phrases related to personal attachment or emotional significance

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

ÑĢÑĸÐ´

-0.17

cela

-0.15

ç´ł

-0.14

asser

-0.14

AWN

-0.14

 Leonard

-0.14

ÏģÎ¬

-0.14

ÙĪØ¦

-0.14

ÐºÑĥÑĢ

-0.14

 ÑģÐ¿ÑĢÑı

-0.14

POSITIVE LOGITS

for

0.27

 Ð´Ð»Ñı

0.21

 pentru

0.21

for

0.20

 untuk

0.20

 fÃ¼r

0.19

 Î³Î¹Î±

0.18

à¸ªà¸³à¸«à¸£

0.17

Ð´Ð»Ñı

0.16

for

0.16

Activations Density 0.063%

words and phrases related to personal attachment or emotional significance

No Comments

No Known Activations