INDEX

Explanations

words related to document creation and composition

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.16

-0.15

arrants

-0.15

iece

-0.15

 Julia

-0.14

xious

-0.14

YPE

-0.14

Ð¾Ð¿Ð¾Ð»

-0.14

 Ground

-0.14

actor

-0.13

POSITIVE LOGITS

ÑĤÐµÑĢÐ¸

0.18

zos

0.16

Ð¾ÑĤÑĭ

0.15

amedi

0.15

eri

0.14

izzer

0.14

 NSCoder

0.14

ilan

0.14

urd

0.14

Ð¾Ð»ÑĮÐ½Ð¾

0.14

Activations Density 0.119%

words related to document creation and composition

No Comments

No Known Activations