INDEX

Explanations

references to language learning applications

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

 computers

-0.19

 Computers

-0.18

 Dell

-0.17

 mouse

-0.17

Mouse

-0.17

ura

-0.16

 mice

-0.16

 Maur

-0.16

mouse

-0.16

 Mouse

-0.16

POSITIVE LOGITS

app

0.26

apk

0.24

APK

0.22

Tap

0.20

Tap

0.20

tap

0.20

android

0.19

App

0.19

 Android

0.19

 tapping

0.19

Activations Density 0.244%

references to language learning applications

No Comments

No Known Activations