INDEX

Explanations

metrics and statistics related to performance and scoring

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

anson

-0.14

obar

-0.14

anton

-0.14

owitz

-0.14

ben

-0.14

identity

-0.14

bar

-0.13

aca

-0.13

 Listings

-0.13

ilik

-0.13

POSITIVE LOGITS

Î»Î±

0.17

era

0.17

eral

0.16

ubl

0.15

Ã³st

0.15

_nbr

0.15

htable

0.14

_ub

0.14

orna

0.14

sid

0.14

Activations Density 0.047%

metrics and statistics related to performance and scoring

No Comments

No Known Activations