INDEX

Explanations

timelines and durations related to events or preparations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

vvm

-0.17

aget

-0.15

ischer

-0.15

æį·

-0.14

Pvt

-0.14

elles

-0.14

Ag

-0.14

.sp

-0.14

vale

-0.14

åĨĴ

-0.14

POSITIVE LOGITS

iew

0.17

etz

0.16

alus

0.16

ogh

0.15

zy

0.14

 nonzero

0.14

tpl

0.14

ibr

0.13

mal

0.13

pre

0.13

Activations Density 0.316%

timelines and durations related to events or preparations

No Comments

No Known Activations