INDEX

Explanations

references to competitive phases or rounds in tournaments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

side

-0.18

sis

-0.18

ãĥĲãĥ¼

-0.15

-INF

-0.15

sign

-0.15

nk

-0.15

ucas

-0.15

inkel

-0.15

uld

-0.14

indir

-0.14

POSITIVE LOGITS

final

0.24

lies

0.21

deck

0.21

-finals

0.20

inals

0.19

-century

0.18

 finals

0.18

lier

0.17

alsy

0.16

 Finals

0.16

Activations Density 0.010%

references to competitive phases or rounds in tournaments

No Comments

No Known Activations