INDEX

Explanations

negative modal verbs indicating possibility or ability

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

 Need

-0.19

Need

-0.18

 need

-0.17

need

-0.17

umen

-0.14

chez

-0.14

Try

-0.14

IfNeeded

-0.14

Try

-0.14

.dom

-0.14

POSITIVE LOGITS

 possibly

0.42

possibly

0.34

 Possibly

0.33

 POSS

0.30

 hope

0.29

hope

0.28

 reasonably

0.27

 afford

0.26

 possible

0.25

 possibility

0.24

Activations Density 0.139%

negative modal verbs indicating possibility or ability

No Comments

No Known Activations