INDEX

Explanations

phrases indicating time or duration within data reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

rang

-0.14

pNet

-0.14

Å¡it

-0.14

ugins

-0.14

ieg

-0.14

riger

-0.14

mai

-0.13

seb

-0.13

 phased

-0.13

ITTER

-0.13

POSITIVE LOGITS

 reporting

0.32

 Reporting

0.27

 rolling

0.25

Reporting

0.24

 sample

0.23

rolling

0.22

 period

0.22

report

0.21

 studied

0.21

 survey

0.21

Activations Density 0.137%

phrases indicating time or duration within data reporting

No Comments

No Known Activations