INDEX

Explanations

instances of the word "way" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

enthal

-0.17

quia

-0.15

sten

-0.15

imid

-0.15

ews

-0.15

imits

-0.15

Î½

-0.14

ranÃŃ

-0.14

ENTE

-0.14

 ServiceException

-0.14

POSITIVE LOGITS

ward

0.22

finding

0.19

ÚĺÙĩ

0.18

rown

0.17

yyy

0.17

yyyy

0.17

oshi

0.17

ÅĽci

0.16

elp

0.16

YYYY

0.15

Activations Density 0.059%

instances of the word "way" in various contexts

No Comments

No Known Activations