INDEX

Explanations

actions related to interacting with files and properties in a computer system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eel

-0.17

ething

-0.17

aqu

-0.16

regist

-0.15

SocketAddress

-0.14

_RAM

-0.14

ÅĻÃŃt

-0.14

eck

-0.14

upertino

-0.13

ystore

-0.13

POSITIVE LOGITS

taÅŁ

0.16

ety

0.16

Ð°ÑĢÐ¾Ð²

0.15

éľŀ

0.14

ITA

0.14

ory

0.14

tails

0.14

æ¡Ĥ

0.14

ä¹ħ

0.14

boru

0.14

Activations Density 0.008%

actions related to interacting with files and properties in a computer system

No Comments

No Known Activations