INDEX

Explanations

modal verbs related to possibility and capability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ushima

-0.16

kovi

-0.15

éģŃ

-0.15

andr

-0.15

entine

-0.15

sv

-0.14

ibur

-0.14

eldon

-0.14

idon

-0.14

Ø§Ø¶

-0.14

POSITIVE LOGITS

pell

0.21

 possibly

0.20

 possible

0.17

possibly

0.17

 Possibly

0.16

 POSS

0.16

Poss

0.15

ummer

0.14

 manage

0.14

fits

0.14

Activations Density 0.035%

modal verbs related to possibility and capability

No Comments

No Known Activations