INDEX

Explanations

ordinal numbers referencing grades or levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

er

-0.16

ogue

-0.15

NotSupportedException

-0.15

ece

-0.14

ÑĩÐ¸Ðº

-0.14

ç¬¬ä¸Ģ

-0.14

erin

-0.14

ski

-0.13

nap

-0.13

eru

-0.13

POSITIVE LOGITS

ousand

0.38

-century

0.38

 century

0.36

 edition

0.32

 Annual

0.31

 anniversary

0.31

-grade

0.30

 percentile

0.30

 grade

0.30

 Anniversary

0.30

Activations Density 0.082%

ordinal numbers referencing grades or levels

No Comments

No Known Activations