INDEX

Explanations

terms related to physical ergonomics and anthropometric measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eh

-0.19

ohn

-0.19

amente

-0.18

ehir

-0.17

ech

-0.17

eel

-0.16

eeee

-0.16

asa

-0.16

isin

-0.16

eam

-0.16

POSITIVE LOGITS

soever

0.28

rd

0.27

ilde

0.20

IGHL

0.19

reesome

0.19

ry

0.18

ertz

0.18

ERSHEY

0.18

hhh

0.17

%%%%%%%%%%%%%%%%

0.17

Activations Density 1.783%

terms related to physical ergonomics and anthropometric measurements

No Comments

No Known Activations