INDEX

Explanations

expressions related to possession or a lack thereof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

not

-0.19

uka

-0.17

ynos

-0.16

 somehow

-0.15

ery

-0.15

ÙĳØ§

-0.15

jen

-0.14

han

-0.14

isk

-0.14

os

-0.14

POSITIVE LOGITS

any

0.40

 anymore

0.38

ä»»ä½ķ

0.29

 anything

0.28

 anyone

0.28

 anybody

0.27

ANY

0.27

.any

0.25

any

0.24

anything

0.24

Activations Density 0.127%

expressions related to possession or a lack thereof

No Comments

No Known Activations