INDEX

Explanations

variations of the word "transform" and related concepts indicating change or improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Wol

-0.16

spiel

-0.16

venir

-0.16

led

-0.15

chooser

-0.15

wig

-0.15

emas

-0.15

apis

-0.15

ifice

-0.15

 Lace

-0.14

POSITIVE LOGITS

al

0.24

ative

0.24

ations

0.23

/trans

0.21

atted

0.20

 Äĳá»ķi

0.17

(Transform

0.17

ulario

0.17

ulas

0.16

.Transform

0.16

Activations Density 0.016%

variations of the word "transform" and related concepts indicating change or improvement

No Comments

No Known Activations