INDEX

Explanations

names of locations or geographic entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

umatic

-0.15

ÑıÐ²Ð¸

-0.14

atical

-0.14

engo

-0.14

eno

-0.14

pcl

-0.14

quito

-0.14

Ð¸Ð¼Ñĥ

-0.13

 Covenant

-0.13

POSITIVE LOGITS

 authDomain

0.16

 Scri

0.15

 Colleg

0.15

etheless

0.15

adena

0.15

\Mapping

0.14

«ĺ

0.14

ValueCollection

0.14

DMI

0.13

.alpha

0.13

Activations Density 0.063%

names of locations or geographic entities

No Comments

No Known Activations