INDEX

Explanations

modal verbs indicating future actions or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

illions

-0.17

Ð¸ÑĢÐ°

-0.15

ussen

-0.15

adal

-0.14

atti

-0.14

orque

-0.14

 BÃĸL

-0.14

leich

-0.14

Çİ

-0.13

levance

-0.13

POSITIVE LOGITS

be

0.37

iam

0.26

iams

0.24

0.23

IAM

0.21

 likely

0.20

nt

0.20

kommen

0.19

not

0.19

/is

0.17

Activations Density 0.340%

modal verbs indicating future actions or possibilities

No Comments

No Known Activations

modal verbs indicating future actions or possibilities

No Comments

No Known Activations