INDEX

Explanations

quantifiable metrics related to statistics, measurements, and data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

plib

-0.15

otte

-0.14

rowsable

-0.14

ÏĢÎ±

-0.14

vale

-0.14

pong

-0.14

ville

-0.13

ajar

-0.13

jar

-0.13

 enum

-0.13

POSITIVE LOGITS

per

0.55

 annually

0.39

_per

0.33

per

0.30

 each

0.29

-per

0.29

Per

0.28

Per

0.28

æ¯ı

0.28

 annual

0.28

Activations Density 0.143%

quantifiable metrics related to statistics, measurements, and data

No Comments

No Known Activations