INDEX

Explanations

references to machine learning model parameters and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

peare

-0.15

nement

-0.15

 neod

-0.14

 Ð²Ð°Ð½

-0.14

libft

-0.14

ADIO

-0.14

ucks

-0.14

utut

-0.14

udas

-0.13

contributors

-0.13

POSITIVE LOGITS

PU

0.17

otec

0.15

ADB

0.14

 autoc

0.14

izzo

0.14

iny

0.13

idi

0.13

 åĿ

0.13

ONY

0.13

 cons

0.13

Activations Density 0.008%

references to machine learning model parameters and configurations

No Comments

No Known Activations