INDEX

Explanations

phrases related to suitability and fit

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Folk

-0.21

 Fellowship

-0.21

 Feder

-0.20

Fallback

-0.20

 Favor

-0.19

Fol

-0.19

 Friendship

-0.19

 Folder

-0.18

 Flooring

-0.18

Fur

-0.17

POSITIVE LOGITS

fit

0.62

-f

0.58

-fit

0.53

 fits

0.49

fit

0.47

.fit

0.44

_fit

0.42

Fit

0.41

Fit

0.40

FIT

0.37

Activations Density 0.123%

phrases related to suitability and fit

No Comments

No Known Activations