INDEX

Explanations

references to dates and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

etto

-0.17

 obec

-0.15

Arb

-0.14

mono

-0.14

quan

-0.14

 Cousins

-0.14

etty

-0.14

Lub

-0.14

ewing

-0.14

etak

-0.14

POSITIVE LOGITS

ilde

0.18

forc

0.15

éª¨

0.15

dol

0.15

 onRequest

0.14

.scalablytyped

0.13

grass

0.13

Specifier

0.13

ilig

0.13

 spol

0.13

Activations Density 0.007%

references to dates and numerical data

No Comments

No Known Activations