INDEX

Explanations

phrases related to searching for and accessing information or products

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ears

-0.17

ÐµÐ»Ð¸Ðº

-0.15

adders

-0.15

lite

-0.15

otes

-0.15

uur

-0.15

leys

-0.14

ansi

-0.14

owie

-0.14

Signals

-0.14

POSITIVE LOGITS

ä¸Ģä¸ĭ

0.18

ä¸įäºĨ

0.16

elson

0.14

DlgItem

0.14

urette

0.14

isay

0.14

inh

0.14

0.13

iry

0.13

à¤¿à¤Ĥ

0.13

Activations Density 0.112%

phrases related to searching for and accessing information or products

No Comments

No Known Activations