INDEX

Explanations

details about updates or changes in specific products or regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

oot

-0.15

Tro

-0.14

çŃĴ

-0.14

/renderer

-0.14

coop

-0.13

pun

-0.13

 vice

-0.13

ERM

-0.13

tv

-0.13

POSITIVE LOGITS

ersiz

0.15

ahoo

0.15

 tháº©m

0.14

 defaultMessage

0.14

ousand

0.14

?family

0.14

_COMPLEX

0.14

umper

0.14

ChangedEventArgs

0.13

ipel

0.13

Activations Density 0.338%

details about updates or changes in specific products or regulations

No Comments

No Known Activations