INDEX

Explanations

instances of the word "to" and its various forms in the context of potential actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Beam

-0.19

Beat

-0.16

 Beam

-0.16

 Beat

-0.15

ibu

-0.14

 nÃ¡m

-0.13

kaar

-0.13

olumn

-0.13

.scalablytyped

-0.13

ÑıÑģÑĮ

-0.13

POSITIVE LOGITS

be

1.18

be

0.63

Be

0.56

 Ø¨Ø§Ø´Ø¯

0.51

be

0.48

Be

0.47

_be

0.45

.be

0.45

 seja

0.43

 Ð±ÑĭÑĤÑĮ

0.41

Activations Density 0.396%

instances of the word "to" and its various forms in the context of potential actions or states

No Comments

No Known Activations