INDEX

Explanations

words related to performance and review metrics

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

 Stap

-0.17

bey

-0.15

ure

-0.15

fu

-0.14

ueva

-0.14

wart

-0.13

Tur

-0.13

/bash

-0.13

-t

-0.13

KS

-0.13

POSITIVE LOGITS

ason

0.17

mina

0.16

acro

0.16

Ã¡c

0.15

idor

0.15

olis

0.15

éħ¸

0.15

idle

0.14

ooter

0.14

anford

0.14

Activations Density 0.053%

words related to performance and review metrics

No Comments

No Known Activations