INDEX

Explanations

quantifiable comparisons related to quantities and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

otime

-0.16

å´

-0.16

acos

-0.15

rippling

-0.14

angi

-0.14

bard

-0.14

 Beyond

-0.14

 Mell

-0.14

esson

-0.14

aniem

-0.14

POSITIVE LOGITS

 ratio

0.21

 equal

0.19

equal

0.19

 Ratio

0.19

Ratio

0.17

 balance

0.17

balance

0.17

ratio

0.17

æ¯Ķä¾ĭ

0.17

 proportion

0.17

Activations Density 0.166%

quantifiable comparisons related to quantities and measurements

No Comments

No Known Activations