INDEX

Explanations

modal verbs indicating necessity or conditional scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Ð¸ÑģÐ¿Ð¾Ð»ÑĮÐ·Ñĥ

-0.14

Ð²Ð¸ÑĩÐ°Ð¹

-0.12

ÌĪ

-0.12

.learn

-0.12

learn

-0.12

unsch

-0.12

_NB

-0.11

indo

-0.11

ÌĨ

-0.11

 zoekt

-0.11

POSITIVE LOGITS

be

0.32

 mean

0.31

 consist

0.30

 include

0.30

 involve

0.29

 occur

0.29

 contain

0.28

 entail

0.28

 exist

0.28

 happen

0.27

Activations Density 0.781%

modal verbs indicating necessity or conditional scenarios

No Comments

No Known Activations