INDEX

Explanations

approximately and roughly quantified data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

hey

-0.17

OOT

-0.16

asil

-0.15

orem

-0.14

ellig

-0.14

pes

-0.14

.au

-0.14

orges

-0.13

isci

-0.13

adnÃŃ

-0.13

POSITIVE LOGITS

 dozen

0.19

 half

0.17

 åįĬ

0.14

.dequeue

0.14

íĥĪ

0.14

olian

0.14

ç¿°

0.14

åįĬ

0.14

.ensure

0.14

UnitTest

0.13

Activations Density 0.084%

approximately and roughly quantified data and statistics

No Comments

No Known Activations