INDEX

Explanations

terminology related to torque and its measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ding

-0.16

kowski

-0.15

 Gang

-0.15

 ting

-0.14

anter

-0.14

mers

-0.14

anga

-0.14

ormal

-0.14

aris

-0.13

ree

-0.13

POSITIVE LOGITS

APON

0.17

entai

0.16

æľ«

0.15

.glide

0.15

prung

0.15

asic

0.14

éļĨ

0.14

ëĭī

0.14

leted

0.14

hift

0.14

Activations Density 0.009%

terminology related to torque and its measurements

No Comments

No Known Activations