INDEX

Explanations

references to various products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

odesk

-0.16

heid

-0.16

_DOC

-0.16

 Giang

-0.15

ump

-0.15

ading

-0.15

dib

-0.15

ibel

-0.14

 overd

-0.14

ern

-0.14

POSITIVE LOGITS

 Ð¿Ð¸ÑĤÐ°Ð½Ð¸Ñı

0.22

ively

0.21

/services

0.21

ivism

0.20

ivities

0.20

eurs

0.19

ivity

0.19

eur

0.18

/service

0.17

onu

0.16

Activations Density 0.060%

references to various products

No Comments

No Known Activations