INDEX

Explanations

financial terms and details related to compensation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ewire

-0.15

anner

-0.15

ãģıãģł

-0.15

å²ģ

-0.15

-0.14

unce

-0.14

abei

-0.14

oor

-0.14

 Jahre

-0.14

Ð·Ñĭ

-0.14

POSITIVE LOGITS

 slot

0.24

 times

0.24

slot

0.23

 peak

0.23

 slots

0.21

Slot

0.21

peak

0.21

-slot

0.20

 Slot

0.20

_slot

0.20

Activations Density 0.172%

financial terms and details related to compensation

No Comments

No Known Activations