INDEX

Explanations

imperative forms of verbs indicating actions or requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

umo

-0.17

ertools

-0.16

found

-0.15

 micron

-0.15

 found

-0.15

 book

-0.15

deb

-0.14

itud

-0.14

out

-0.14

iversit

-0.14

POSITIVE LOGITS

ursal

0.15

Ã¡v

0.14

-urlencoded

0.14

arching

0.14

hof

0.13

bane

0.13

ìŀ¡

0.13

 znam

0.13

aepernick

0.13

Ð¾ÑĩÐ½Ð¾

0.13

Activations Density 0.235%

imperative forms of verbs indicating actions or requests

No Comments

No Known Activations