INDEX

Explanations

words related to the presence of vulnerability and support within communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ãĤ¡

-0.16

duit

-0.15

Î³Î¿Ïį

-0.15

mand

-0.15

odor

-0.14

ÅĽnie

-0.14

åĽ½ãģ®

-0.14

.AppSettings

-0.14

inski

-0.14

_CPP

-0.13

POSITIVE LOGITS

its

0.15

beginTransaction

0.14

avicon

0.14

otional

0.14

ClassLoader

0.13

urement

0.13

isode

0.13

essenger

0.13

argo

0.13

 Ð²Ð¾ÑĤ

0.13

Activations Density 0.260%

words related to the presence of vulnerability and support within communities

No Comments

No Known Activations