INDEX

Explanations

instances of the phrase "don't be."

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

aybe

-0.16

bage

-0.15

ghan

-0.14

ÑĢÐ°Ð²Ð°

-0.14

lest

-0.14

abei

-0.14

ADI

-0.14

andi

-0.14

isses

-0.14

stoup

-0.14

POSITIVE LOGITS

 worry

0.18

/do

0.17

Go

0.16

Go

0.16

oice

0.16

 forget

0.16

 Allen

0.16

Allen

0.15

 Forget

0.15

go

0.15

Activations Density 0.033%

instances of the phrase "don't be."

No Comments

No Known Activations