INDEX

Explanations

phrases indicating the completion of actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-0.18

loff

-0.15

lla

-0.15

Ø§ÛĮØ´

-0.14

Hem

-0.14

itte

-0.14

_stub

-0.14

.ua

-0.14

´Ŀ

-0.14

amil

-0.13

POSITIVE LOGITS

usher

0.18

ORITY

0.14

airy

0.13

tsy

0.13

orrow

0.13

 createSelector

0.13

 Riot

0.13

ored

0.13

ãĥ¼ãĥĸãĥ«

0.13

endor

0.13

Activations Density 0.011%

phrases indicating the completion of actions or events

No Comments

No Known Activations