INDEX

Explanations

words and phrases indicating proximity, ownership, and quality, often in a context related to health or environmental factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

amber

-0.16

datable

-0.15

ÑĤÐ¸Ñı

-0.14

Ð¾Ð¾Ð±ÑĢÐ°Ð·

-0.14

DECLARE

-0.14

antro

-0.14

anos

-0.14

arf

-0.14

umber

-0.13

 security

-0.13

POSITIVE LOGITS

esktop

0.15

ropoda

0.14

gs

0.14

ÄĽt

0.14

APON

0.14

ients

0.14

ÙĦÙĤ

0.14

zk

0.13

lic

0.13

_PROPERTY

0.13

Activations Density 0.026%

words and phrases indicating proximity, ownership, and quality, often in a context related to health or environmental factors

No Comments

No Known Activations