INDEX

Explanations

references to the name "Nibali" and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ynes

-0.16

amine

-0.15

icles

-0.15

icana

-0.14

illez

-0.14

ubit

-0.14

éĻ

-0.14

 goodness

-0.14

ersen

-0.14

ãĥ³ãĥĲ

-0.14

POSITIVE LOGITS

rawl

0.15

bery

0.15

TNT

0.15

bons

0.15

ascus

0.14

etal

0.14

.liferay

0.14

PD

0.14

 Covered

0.14

bern

0.13

Activations Density 0.027%

references to the name "Nibali" and variations of it

No Comments

No Known Activations