INDEX

Explanations

instances of the word "sun" or its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

dorf

-0.22

enton

-0.16

gov

-0.15

cheng

-0.14

opher

-0.14

cum

-0.14

leans

-0.14

cx

-0.14

omor

-0.14

POSITIVE LOGITS

ken

0.33

flower

0.31

sets

0.28

flowers

0.26

burst

0.26

nier

0.25

niest

0.25

 Microsystems

0.25

rise

0.24

screens

0.24

Activations Density 0.025%

instances of the word "sun" or its variations

No Comments

No Known Activations