INDEX

Explanations

references to apples and related products

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

.scalablytyped

-0.17

edin

-0.17

_IOC

-0.16

Ã¼hl

-0.15

èį

-0.15

aurus

-0.14

_RC

-0.14

weed

-0.14

-addons

-0.14

meer

-0.14

POSITIVE LOGITS

 apple

0.51

 apples

0.46

 Apple

0.45

 cider

0.43

apple

0.43

Apple

0.40

èĭ¹æŀľ

0.39

 APPLE

0.38

/apple

0.34

APPLE

0.33

Activations Density 0.031%

references to apples and related products

No Comments

No Known Activations