INDEX

Explanations

references to scientific journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Alb

-0.16

 gest

-0.15

Meh

-0.15

ante

-0.15

olik

-0.15

adar

-0.14

ocop

-0.14

atk

-0.14

 sulf

-0.14

anners

-0.14

POSITIVE LOGITS

 Nature

0.26

Nature

0.25

npj

0.25

 nature

0.22

nature

0.20

Pointer

0.16

_EXTENDED

0.16

dataArray

0.16

ATURE

0.15

Nat

0.15

Activations Density 0.030%

references to scientific journals and publications

No Comments

No Known Activations