INDEX

Explanations

items or features that are equipped with specific characteristics or components

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

emsp

-0.16

eah

-0.15

æ¢¨

-0.15

ihan

-0.15

 shaken

-0.14

.Modules

-0.13

ief

-0.13

 AuthenticationService

-0.13

aira

-0.13

xee

-0.13

POSITIVE LOGITS

ery

0.17

enet

0.15

enheim

0.14

ionage

0.14

enso

0.14

itung

0.14

noi

0.13

Ð²Ð°ÑĤ

0.13

cher

0.13

ugh

0.13

Activations Density 0.015%

items or features that are equipped with specific characteristics or components

No Comments

No Known Activations