INDEX

Explanations

references to averages in statistics or performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

les

-0.17

yc

-0.15

idel

-0.15

erk

-0.14

Ð»ÑĥÑĪ

-0.14

/fw

-0.14

sth

-0.14

 Shooter

-0.14

stants

-0.14

-mode

-0.14

POSITIVE LOGITS

WORD

0.14

iveau

0.14

Campo

0.14

ampo

0.14

ltk

0.14

dic

0.14

ncmp

0.13

quete

0.13

eature

0.13

ataire

0.13

Activations Density 0.015%

references to averages in statistics or performance metrics

No Comments

No Known Activations

references to averages in statistics or performance metrics

No Comments

No Known Activations