INDEX

Explanations

terms related to customization or personalized services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

uta

-0.17

OLON

-0.16

iÃ©n

-0.16

 Tears

-0.15

alia

-0.15

 tears

-0.15

bour

-0.15

 tear

-0.14

asp

-0.14

jang

-0.14

POSITIVE LOGITS

addtogroup

0.16

Sit

0.16

du

0.16

ponential

0.15

 situ

0.15

ŀ

0.15

uddy

0.15

reesome

0.15

cube

0.14

Sit

0.14

Activations Density 0.004%

terms related to customization or personalized services

No Comments

No Known Activations