INDEX

Explanations

phrases indicating unavailability or issues with information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Aggregate

-0.14

¢°

-0.14

assage

-0.14

aggregate

-0.14

bers

-0.14

amber

-0.14

-0.13

utter

-0.13

áº¯ng

-0.13

POSITIVE LOGITS

eline

0.17

enheim

0.15

esseract

0.15

arker

0.14

vÄĽÅĻ

0.14

ENER

0.14

Ã¤ft

0.14

ael

0.14

RTOS

0.14

.XR

0.14

Activations Density 0.188%

phrases indicating unavailability or issues with information

No Comments

No Known Activations