INDEX

Explanations

potential capabilities and functionalities of objects or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

anes

-0.16

Ïİ

-0.15

ator

-0.15

 sant

-0.14

 kulak

-0.14

wich

-0.14

ieur

-0.14

 anlam

-0.13

 Abed

-0.13

uC

-0.13

POSITIVE LOGITS

idata

0.18

 provide

0.15

 æĽ

0.15

asio

0.14

YLES

0.14

dna

0.14

 Provide

0.14

 produce

0.14

 providing

0.14

Activations Density 0.176%

potential capabilities and functionalities of objects or systems

No Comments

No Known Activations