INDEX

Explanations

phrases indicating the passage of time or duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

/or

-0.17

gia

-0.17

/on

-0.16

fter

-0.15

/her

-0.15

ulpt

-0.15

ç¨ĭåº¦

-0.14

ifice

-0.14

Ú¯Ø±

-0.14

ãĥ¼ãĥĹ

-0.14

POSITIVE LOGITS

WithContext

0.17

dere

0.15

?key

0.15

/generated

0.14

eel

0.14

/render

0.13

us

0.13

 Äĳáº©y

0.13

ercul

0.13

Ã¡li

0.13

Activations Density 0.051%

phrases indicating the passage of time or duration

No Comments

No Known Activations