INDEX

Explanations

references to literary figures and works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ø´Ø©

-0.16

Ð»Ð°Ð´Ð°

-0.15

etro

-0.15

occo

-0.14

ordo

-0.14

awi

-0.13

odo

-0.13

unh

-0.13

ldata

-0.13

 Bieber

-0.13

POSITIVE LOGITS

Å¯v

0.16

ibase

0.15

athon

0.15

rella

0.15

Interstitial

0.15

ynet

0.14

haar

0.14

iali

0.14

 Ends

0.14

 Extras

0.14

Activations Density 0.082%

references to literary figures and works

No Comments

No Known Activations