INDEX

Explanations

the occurrence of the word "my" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.20

ables

-0.15

DEX

-0.14

able

-0.14

preview

-0.14

ItemList

-0.14

Ãªt

-0.14

ilities

-0.14

 shoulder

-0.14

tml

-0.14

POSITIVE LOGITS

self

0.21

batis

0.19

SELF

0.17

anmar

0.16

/the

0.15

 Ã¶zel

0.15

own

0.15

ìĤ¬ìĿĺ

0.14

 nÃ¸

0.14

embro

0.14

Activations Density 0.018%

the occurrence of the word "my" and its variations in different contexts

No Comments

No Known Activations