INDEX

Explanations

references to specific geographic locations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Mature

-0.16

ENU

-0.15

incy

-0.14

 mature

-0.14

vature

-0.14

uch

-0.14

ÏĦÎ¿Îº

-0.14

amble

-0.13

etz

-0.13

POSITIVE LOGITS

.cf

0.17

ruta

0.15

éĳ

0.15

arkers

0.15

iram

0.15

æ¢¨

0.14

 Chance

0.14

ovel

0.14

_chance

0.14

Chance

0.14

Activations Density 0.030%

references to specific geographic locations or entities

No Comments

No Known Activations