INDEX

Explanations

references to bibliographic elements or structured data in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ersh

-0.16

ynes

-0.15

ampa

-0.15

Ð°ÑĤÐ¾Ðº

-0.15

atform

-0.15

zier

-0.14

rescia

-0.14

è¨

-0.14

reau

-0.14

åĲ§

-0.14

POSITIVE LOGITS

ointment

0.17

ackbar

0.17

ido

0.16

 Toni

0.15

viso

0.15

coin

0.14

occasion

0.14

idos

0.14

ibraries

0.14

 Marie

0.14

Activations Density 0.003%

references to bibliographic elements or structured data in documents

No Comments

No Known Activations