INDEX

Explanations

references to quality measures and 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÑĥÐ»ÑĮ

-0.16

bove

-0.15

atti

-0.15

atoria

-0.14

tle

-0.14

jah

-0.13

unnel

-0.13

Î³ÏģÎ±ÏĨ

-0.13

ado

-0.13

wave

-0.13

POSITIVE LOGITS

_tpl

0.16

_lite

0.15

 takson

0.15

fcn

0.14

Ú©Øª

0.14

Ken

0.14

 Fres

0.13

maal

0.13

lob

0.13

 opens

0.13

Activations Density 0.002%

references to quality measures and performance metrics

No Comments

No Known Activations