INDEX

Explanations

references to confidentiality and legal obligations in a medical or research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Roland

-0.14

ÙĪØ¯Ø©

-0.14

redo

-0.14

SizeMode

-0.13

uffy

-0.13

eldorf

-0.13

addir

-0.13

/popper

-0.12

Ð¾Ð²Ð°Ð½Ñĸ

-0.12

acman

-0.12

POSITIVE LOGITS

 report

1.23

 reports

1.05

 Report

1.03

report

1.02

-report

0.97

 REPORT

0.96

Report

0.96

 reporting

0.95

.report

0.91

_report

0.90

Activations Density 0.244%

references to confidentiality and legal obligations in a medical or research context

No Comments

No Known Activations