INDEX

Explanations

sequences of numbers and identifiers related to events or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 confront

-0.17

oka

-0.15

orny

-0.14

æı¡

-0.13

os

-0.13

uri

-0.13

agle

-0.13

unk

-0.13

aging

-0.13

ua

-0.13

POSITIVE LOGITS

ORIZ

0.17

ãĥ¼ãĥŃ

0.16

sei

0.16

URED

0.15

etur

0.15

VES

0.14

gregated

0.14

ceae

0.14

uner

0.14

 hÃ´m

0.14

Activations Density 0.006%

sequences of numbers and identifiers related to events or organizations

No Comments

No Known Activations