INDEX

Explanations

terms related to identifiers and their functionalities within a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Å¡e

-0.15

anuts

-0.15

clist

-0.14

ukt

-0.14

pcf

-0.14

ãģ¯ãģļ

-0.14

ãĥ³ãĥĩ

-0.13

chu

-0.13

msp

-0.13

env

-0.13

POSITIVE LOGITS

 easily

0.23

 Easily

0.20

 easy

0.20

 kolay

0.20

 easier

0.20

.easy

0.19

 Easy

0.18

æĺĵ

0.18

Easy

0.17

å®¹æĺĵ

0.17

Activations Density 0.201%

terms related to identifiers and their functionalities within a system

No Comments

No Known Activations