INDEX

Explanations

references to warranties and product specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

chwitz

-0.16

olini

-0.16

benh

-0.15

mÃ¼r

-0.15

 Aires

-0.14

 stun

-0.14

anches

-0.14

apeut

-0.14

iez

-0.14

ÐµÑĢÐ°Ð¿

-0.14

POSITIVE LOGITS

 lubric

0.26

 oils

0.24

oil

0.24

Oil

0.22

lub

0.22

 engine

0.22

Lub

0.20

Oil

0.20

 Engine

0.19

 fluid

0.19

Activations Density 0.045%

references to warranties and product specifications

No Comments

No Known Activations