INDEX

Explanations

references to supercomputing and related institutions or concepts

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

_WARNINGS

-0.21

eway

-0.17

ivent

-0.16

endir

-0.15

mpl

-0.15

ÐµÐ½Ð´

-0.15

opak

-0.15

å¡

-0.15

omba

-0.15

unte

-0.14

POSITIVE LOGITS

Ð»Ñİ

0.15

ida

0.15

/dashboard

0.14

 Convers

0.13

iron

0.13

Lug

0.13

Cr

0.13

 verdi

0.13

åĩĮ

0.13

Activations Density 0.012%

references to supercomputing and related institutions or concepts

No Comments

No Known Activations