INDEX

Explanations

the word "forever" and related variations, indicating a focus on permanence or lasting concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Liberties

-0.14

Ã©tÃ©

-0.14

elle

-0.14

 bitte

-0.14

ecc

-0.14

 tÃłi

-0.14

ayo

-0.14

ulty

-0.13

ombre

-0.13

Lt

-0.13

POSITIVE LOGITS

greens

0.19

 Forever

0.17

green

0.17

icals

0.16

hin

0.16

lasting

0.16

Å¥

0.16

 forever

0.16

-lasting

0.16

iets

0.16

Activations Density 0.025%

the word "forever" and related variations, indicating a focus on permanence or lasting concepts

No Comments

No Known Activations