INDEX

Explanations

instances of necessity or obligation expressed through the word "must"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 maybe

-0.16

ropoda

-0.16

Ä±sÄ±t

-0.16

roperty

-0.15

onz

-0.15

orno

-0.15

ibbon

-0.15

leich

-0.15

apos

-0.14

posite

-0.14

POSITIVE LOGITS

0.26

be

0.24

ache

0.23

-have

0.22

ering

0.20

ered

0.20

aches

0.18

afa

0.18

 surely

0.17

angs

0.17

Activations Density 0.039%

instances of necessity or obligation expressed through the word "must"

No Comments

No Known Activations